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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Female
    -0.08
    idente
    -0.07
    .feature
    -0.07
    avic
    -0.06
    Verts
    -0.06
    ߛ
    -0.06
    Die
    -0.06
     Speakers
    -0.06
     offspring
    -0.06
     NotificationCenter
    -0.06
    POSITIVE LOGITS
     polymer
    0.07
     организация
    0.07
    userinfo
    0.07
    _COMPANY
    0.07
     yans
    0.07
     USED
    0.06
     bor
    0.06
    大多
    0.06
     Pills
    0.06
    實施
    0.06
    Act Density 0.023%

    No Known Activations