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

    Neuronpedia

    INDEX
    Explanations

    statistical significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cob
    -0.07
     Stack
    -0.07
    rish
    -0.07
     pave
    -0.07
     вони
    -0.06
    ARIO
    -0.06
     IMPLEMENT
    -0.06
     Trusted
    -0.06
    673
    -0.06
    .histogram
    -0.06
    POSITIVE LOGITS
     obtaining
    0.06
    ;}
↵
    0.06
     피
    0.06
    ursively
    0.06
    ElapsedTime
    0.06
     recursively
    0.06
    OPY
    0.06
     Iter
    0.06
    copy
    0.06
    ffects
    0.06
    Act Density 0.004%

    No Known Activations