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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    纳
    -0.07
    remaining
    -0.07
    救治
    -0.07
    קיימים
    -0.07
    “It
    -0.06
    iven
    -0.06
     שונות
    -0.06
    ck
    -0.06
    you
    -0.06
    iner
    -0.06
    POSITIVE LOGITS
    Degree
    0.08
    -board
    0.07
    (calc
    0.07
    🎏
    0.07
    ＄
    0.07
    .office
    0.07
    (Role
    0.07
    .RGB
    0.07
    gf
    0.07
     Ведь
    0.07
    Act Density 2.134%

    No Known Activations