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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jsme
    -0.06
    _EXISTS
    -0.06
    rně
    -0.06
    pherd
    -0.06
    的情况
    -0.06
     گرد
    -0.05
     Quarter
    -0.05
    mith
    -0.05
     голова
    -0.05
     στους
    -0.05
    POSITIVE LOGITS
    earning
    0.07
     Seamless
    0.07
    owners
    0.06
    iv
    0.06
     Scoped
    0.06
    (Function
    0.06
    odule
    0.06
     sert
    0.06
     Eating
    0.06
    panic
    0.06
    Act Density 0.010%

    No Known Activations