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

    Neuronpedia

    INDEX
    Explanations

    actions and phrases indicating personal involvement or commitment

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

    actions, states, or progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.57
    -0.56
    ValueStyle
    -0.52
     niebla
    -0.52
     tranquilidad
    -0.51
     cuarzo
    -0.51
     psicológico
    -0.50
     '\\;'
    -0.50
     alrededores
    -0.48
    Diweddarwch
    -0.48
    POSITIVE LOGITS
     enf
    0.47
    hpur
    0.46
    ésult
    0.46
    蚪
    0.44
    刮
    0.44
    uxxxx
    0.41
     vestig
    0.40
     dimer
    0.40
     pi
    0.40
     mut
    0.39
    Act Density 0.659%

    No Known Activations