Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of criticism or dissatisfaction regarding actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    behavior or actions

    np_acts-logits-general · gemini-2.0-flash

    actions and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mapStateToProps
    -0.61
     convient
    -0.53
    حق
    -0.52
    ReusableCell
    -0.52
    Gef
    -0.50
    ಾಯ
    -0.47
     NSCoder
    -0.47
     mulighed
    -0.47
    MemoryWarning
    -0.47
    koning
    -0.46
    POSITIVE LOGITS
     behaviour
    0.69
     חיצוניים
    0.66
     behavior
    0.63
    Behaviors
    0.63
     Behaviour
    0.62
     gedrag
    0.59
    behavior
    0.59
    ออกมา
    0.58
     behaviours
    0.57
     actions
    0.57
    Act Density 0.622%

    No Known Activations