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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     savor
    -0.08
     dread
    -0.08
    ിനിമ
    -0.08
     inhabit
    -0.07
     Lovely
    -0.07
    vre
    -0.07
     Paste
    -0.07
    _point
    -0.07
     vivid
    -0.07
     pastime
    -0.07
    POSITIVE LOGITS
     leverancier
    0.08
     عام
    0.08
    _supplier
    0.08
    Velocity
    0.08
     onwards
    0.07
     Velocity
    0.07
    Developer
    0.07
    ಗಳಲ್ಲಿ
    0.07
     toxicity
    0.07
    201
    0.07
    Act Density 0.045%

    No Known Activations