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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kd
    -0.07
     '+
    -0.07
     yol
    -0.06
     fon
    -0.06
     resilient
    -0.06
    arResult
    -0.06
    -sw
    -0.06
     싱
    -0.06
    &quot
    -0.06
    dict
    -0.06
    POSITIVE LOGITS
     acknowledgment
    0.07
     на
    0.07
    entes
    0.07
     псих
    0.06
    þ
    0.06
    ês
    0.06
     piled
    0.06
    dez
    0.06
     начинает
    0.06
     collusion
    0.06
    Act Density 0.001%

    No Known Activations