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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or locations

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

    fields of academic study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.46
    phosa
    -0.44
    RP
    -0.40
    OpenAPI
    -0.40
    OJ
    -0.39
    JP
    -0.39
    舺
    -0.39
    upol
    -0.39
    TabStop
    -0.38
    StateManager
    -0.38
    POSITIVE LOGITS
    calaureate
    0.59
     للمعارف
    0.57
    findpost
    0.56
     graduate
    0.55
     doctorate
    0.51
    inSlope
    0.50
    bibfield
    0.48
    posedge
    0.48
    graduate
    0.48
     Infórmanos
    0.48
    Act Density 0.005%

    No Known Activations