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

    Neuronpedia

    INDEX
    Explanations

    GUI elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _chunks
    -0.07
    represented
    -0.07
    Confidence
    -0.07
     vulnerabilities
    -0.07
    _training
    -0.07
     कमजोर
    -0.07
    Restrictions
    -0.07
    field
    -0.07
    -0.07
    Vari
    -0.07
    POSITIVE LOGITS
    .floor
    0.08
    �
    0.08
     उज
    0.08
     logos
    0.08
    Laptop
    0.08
     кнопку
    0.08
     компьют
    0.07
     Lod
    0.07
     inspira
    0.07
    牌
    0.07
    Act Density 0.005%
    No Known Activations