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

    Neuronpedia

    INDEX
    Explanations

    Opinions and personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Franti
    -0.07
     гиб
    -0.06
     fluores
    -0.06
    низ
    -0.06
     Levin
    -0.06
     petite
    -0.06
     Σεπ
    -0.06
     건
    -0.06
     righteousness
    -0.06
    Controls
    -0.06
    POSITIVE LOGITS
     olmadığını
    0.07
    (es
    0.07
    .messaging
    0.06
    .•
    0.06
    ा।↵
    0.06
    كن
    0.06
    če
    0.06
     validations
    0.06
     kW
    0.06
     implants
    0.06
    Act Density 0.032%

    No Known Activations