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

    Neuronpedia

    INDEX
    Explanations

    album

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    .Tasks
    -0.07
     wym
    -0.07
    \helpers
    -0.06
     Guar
    -0.06
    入れ
    -0.06
     fotbal
    -0.06
     cola
    -0.06
    baar
    -0.06
    气
    -0.06
    POSITIVE LOGITS
    (condition
    0.06
    pixels
    0.06
     revolutionary
    0.06
     Context
    0.06
     případě
    0.06
     Throw
    0.06
    Chuck
    0.06
     cocktail
    0.06
     مد
    0.06
    各种
    0.06
    Act Density 0.007%

    No Known Activations