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

    Neuronpedia

    INDEX
    Explanations

    Waiting areas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tra
    -0.08
     contra
    -0.07
    ,vector
    -0.07
    Det
    -0.07
    pj
    -0.07
    ߥ
    -0.07
    텉
    -0.07
    ResponseType
    -0.07
    ",
    -0.07
    봉
    -0.07
    POSITIVE LOGITS
    ospels
    0.07
    jectives
    0.07
    قول
    0.07
    (deg
    0.07
    elage
    0.07
     �
    0.07
     себ
    0.06
     WriteLine
    0.06
     ein
    0.06
     kuruluş
    0.06
    Act Density 0.059%

    No Known Activations