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
    peq
    -0.07
     lok
    -0.07
    庆祝
    -0.07
    称为
    -0.07
    有关
    -0.06
    icularly
    -0.06
     gameTime
    -0.06
    .mass
    -0.06
     hands
    -0.06
    .Pre
    -0.06
    POSITIVE LOGITS
    "];↵
    0.07
    Trail
    0.07
     deterrent
    0.07
    すぐ
    0.07
     فهو
    0.07
     disclosures
    0.07
     Funeral
    0.06
    Removing
    0.06
    玠
    0.06
    in
    0.06
    Act Density 0.125%

    No Known Activations