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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新鲜
    -0.07
    אז
    -0.07
    增高
    -0.07
    =User
    -0.07
    🕓
    -0.07
    -Nazi
    -0.07
    .damage
    -0.07
     eig
    -0.06
    egot
    -0.06
     infants
    -0.06
    POSITIVE LOGITS
    rt
    0.07
    amac
    0.07
    uru
    0.07
    _ml
    0.06
    ᇂ
    0.06
    Packet
    0.06
     Commerce
    0.06
    .Proxy
    0.06
    师兄
    0.06
     lf
    0.06
    Act Density 0.152%

    No Known Activations