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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +#+
    -0.06
    ABLE
    -0.06
     phenotype
    -0.06
    ulfilled
    -0.06
    (GameObject
    -0.06
    уру
    -0.06
    Period
    -0.06
    ;
↵
↵
↵
    -0.06
     proposing
    -0.06
    UFFER
    -0.06
    POSITIVE LOGITS
    /graphql
    0.08
    .sin
    0.07
    112
    0.07
    .vn
    0.06
    116
    0.06
    .spatial
    0.06
    jest
    0.06
     마법
    0.06
    (sentence
    0.06
     حد
    0.06
    Act Density 0.052%

    No Known Activations