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

    Neuronpedia

    INDEX
    Explanations

    Code snippets/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gel
    -0.07
    Visit
    -0.07
     baru
    -0.07
    _Output
    -0.07
    UY
    -0.06
     KA
    -0.06
    [column
    -0.06
    ="'.$
    -0.06
     collecting
    -0.06
    aptops
    -0.06
    POSITIVE LOGITS
    gran
    0.07
     reasonably
    0.07
    عدل
    0.07
    PermissionsResult
    0.07
    .github
    0.06
     بيان
    0.06
     najb
    0.06
     atroc
    0.06
    超过
    0.06
    apache
    0.06
    Act Density 0.141%

    No Known Activations