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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Idle
    -0.08
    Bearer
    -0.07
    �
    -0.07
     bn
    -0.07
    -ser
    -0.06
    Robert
    -0.06
    StringLength
    -0.06
     Garr
    -0.06
     squarely
    -0.06
    Maint
    -0.06
    POSITIVE LOGITS
    ็็
    0.07
    gricult
    0.06
     delightful
    0.06
    entine
    0.06
    ozí
    0.06
    ać
    0.06
    .DefaultCellStyle
    0.06
     فایل
    0.06
    ................................................................
    0.06
    ummy
    0.06
    Act Density 0.039%

    No Known Activations