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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Output
    -0.07
     concussion
    -0.07
    .Run
    -0.06
    \Type
    -0.06
    129
    -0.06
     decoder
    -0.06
    /mark
    -0.06
     fw
    -0.06
    982
    -0.06
     五
    -0.06
    POSITIVE LOGITS
    arseille
    0.07
    idak
    0.06
    irmingham
    0.06
     důvodu
    0.06
     Strategies
    0.06
     signIn
    0.06
    preserve
    0.06
     Sharks
    0.06
     прост
    0.06
     Конститу
    0.06
    Act Density 0.002%

    No Known Activations