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

    Neuronpedia

    INDEX
    Explanations

    software design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     congregation
    -0.08
    _literal
    -0.06
     administrators
    -0.06
    -0.06
    颜
    -0.06
     mothers
    -0.06
    -functional
    -0.06
     Carey
    -0.06
    -0.06
    ors
    -0.06
    POSITIVE LOGITS
    NM
    0.07
     navigationOptions
    0.07
     پذیر
    0.07
    uko
    0.07
     TED
    0.07
    克斯
    0.07
    OCKET
    0.07
     downhill
    0.06
    ERSHEY
    0.06
     ola
    0.06
    Act Density 0.035%

    No Known Activations