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

    Neuronpedia

    INDEX
    Explanations

    requires immediate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    代表人
    0.67
     inoculum
    0.66
    螨
    0.64
    ^{-
    0.63
    PTR
    0.63
    ANA
    0.60
    猜测
    0.59
    ittance
    0.59
    ধু
    0.58
    anaan
    0.58
    POSITIVE LOGITS
     emergency
    3.66
    Emergency
    3.49
     Emergency
    3.46
     urgent
    3.44
     emergencies
    3.41
    emergency
    3.40
    紧急
    3.17
     Urgent
    3.15
    緊急
    3.08
     EMERGENCY
    3.08
    Act Density 0.432%

    No Known Activations