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

    Neuronpedia

    INDEX
    Explanations

    Article/code excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standards
    -0.08
     Rehab
    -0.07
     Cardiff
    -0.06
    NULL
    -0.06
    unic
    -0.06
     Standards
    -0.06
    .bundle
    -0.06
     prey
    -0.06
     Petr
    -0.06
     Tour
    -0.06
    POSITIVE LOGITS
    ieren
    0.06
    擦
    0.06
    施工
    0.06
     cried
    0.06
    nuts
    0.05
     còn
    0.05
    hashed
    0.05
    than
    0.05
    نام
    0.05
    هدف
    0.05
    Act Density 0.289%

    No Known Activations