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

    Neuronpedia

    INDEX
    Explanations

    defaultdict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antas
    -0.07
     dismant
    -0.06
     tempor
    -0.06
     Rob
    -0.06
    .organ
    -0.06
    .pipe
    -0.06
    ugi
    -0.06
    тый
    -0.06
     Extreme
    -0.06
    Bring
    -0.06
    POSITIVE LOGITS
    paired
    0.07
     defaultdict
    0.07
    policy
    0.06
     reprint
    0.06
    nilai
    0.06
    Format
    0.06
    wizard
    0.06
     ISSUE
    0.06
     새
    0.06
    conditions
    0.06
    Act Density 0.000%

    No Known Activations