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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nm
    -0.07
    phalt
    -0.07
    look
    -0.06
     Slice
    -0.06
    IGNAL
    -0.06
    HELL
    -0.06
    .land
    -0.06
     NUIT
    -0.06
    Checkpoint
    -0.06
     pav
    -0.06
    POSITIVE LOGITS
    相近
    0.07
    福利
    0.07
     likely
    0.06
     //[
    0.06
    duplicate
    0.06
    法人
    0.06
    等原因
    0.06
    轱
    0.06
    キャラ
    0.06
     [])↵
    0.06
    Act Density 0.008%

    No Known Activations