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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and limitations

    np_max-act · gemini-2.0-flash

    The neuron detects the word “Nothing” used to introduce disclaimer statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rad
    -0.07
    _Equals
    -0.07
    SYNC
    -0.07
     label
    -0.07
     susceptibility
    -0.06
    +'.
    -0.06
    /modules
    -0.06
     پوش
    -0.06
    SIZE
    -0.06
     //=
    -0.06
    POSITIVE LOGITS
    .u
    0.06
     No
    0.06
    :^(
    0.06
     hydration
    0.06
    lected
    0.06
     Giang
    0.06
    No
    0.06
    "No
    0.06
     제
    0.06
     embracing
    0.06
    Act Density 0.005%

    No Known Activations