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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    middle
    -0.06
     nawet
    -0.06
     onload
    -0.06
    devices
    -0.06
    GRID
    -0.06
    orld
    -0.06
    ял
    -0.06
    idenav
    -0.06
     нескольких
    -0.06
     ngũ
    -0.06
    POSITIVE LOGITS
    erable
    0.07
     Assistance
    0.07
    .Navigate
    0.06
    atıcı
    0.06
     Growth
    0.06
    .cid
    0.06
    udes
    0.06
     Once
    0.06
     NBC
    0.06
     Poke
    0.06
    Act Density 0.023%

    No Known Activations