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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancers
    -0.07
    (pc
    -0.06
     ・
    -0.06
     บร
    -0.06
    -login
    -0.06
     actu
    -0.06
    Checkpoint
    -0.06
     Ket
    -0.06
     Films
    -0.06
                  ↵
    -0.06
    POSITIVE LOGITS
    說
    0.07
    Stan
    0.07
    _PRIV
    0.06
     abusing
    0.06
    order
    0.06
    +',
    0.06
    artifact
    0.06
    datum
    0.06
     PRIV
    0.06
     Moved
    0.06
    Act Density 0.030%

    No Known Activations