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

    Neuronpedia

    INDEX
    Explanations

    Subscriptions and user accounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nichols
    -0.07
     Partners
    -0.07
    要做
    -0.07
    做
    -0.07
     defects
    -0.07
     infections
    -0.07
     Fro
    -0.07
     nad
    -0.06
     Down
    -0.06
    儿女
    -0.06
    POSITIVE LOGITS
    ==============↵
    0.07
    سكر
    0.07
    metatable
    0.07
    gota
    0.07
    齒
    0.06
    שתמש
    0.06
    .num
    0.06
     cư
    0.06
    装
    0.06
     Critics
    0.06
    Act Density 0.704%

    No Known Activations