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

    Neuronpedia

    INDEX
    Explanations

    News and reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sloan
    -0.07
    nod
    -0.07
    .break
    -0.06
    161
    -0.06
     �
    -0.06
    �
    -0.06
    _THAT
    -0.06
    (kwargs
    -0.06
    mouse
    -0.06
    _vc
    -0.06
    POSITIVE LOGITS
     Mash
    0.06
     discounts
    0.06
    ώνα
    0.06
     Devils
    0.06
    رض
    0.06
     Hur
    0.06
     activists
    0.06
    тора
    0.06
     yards
    0.06
    /us
    0.06
    Act Density 1.304%

    No Known Activations