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

    Neuronpedia

    INDEX
    Explanations

    atory

    np_max-act · gemini-2.0-flash

    instances of derogatory language and inappropriate requests.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     chip
    -0.06
    _classes
    -0.06
    �
    -0.06
    \a
    -0.06
     cycle
    -0.06
     LiveData
    -0.06
     Feast
    -0.06
    .cond
    -0.06
     buluş
    -0.06
    Safe
    -0.06
    POSITIVE LOGITS
    updated
    0.07
     guardian
    0.07
     sincerely
    0.07
     dando
    0.06
    ilitary
    0.06
     SPDX
    0.06
     unchanged
    0.06
    ARY
    0.06
    Comparer
    0.06
     decorator
    0.06
    Act Density 0.006%

    No Known Activations