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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Igor
    -0.07
     Tax
    -0.07
    Xi
    -0.06
     menstr
    -0.06
    😚
    -0.06
     moz
    -0.06
    .mi
    -0.06
     Budget
    -0.06
    ໃ
    -0.06
     ceremon
    -0.06
    POSITIVE LOGITS
    puted
    0.08
     cây
    0.08
    Investigators
    0.07
    _signals
    0.07
    cover
    0.07
    所谓
    0.07
    relationship
    0.07
    continent
    0.07
    essed
    0.06
     Test
    0.06
    Act Density 0.039%

    No Known Activations