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

    Neuronpedia

    INDEX
    Explanations

    references to source materials or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code and documentation references

    np_acts-logits-general · gemini-2.0-flash

    reference points or implementations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.54
    ーション
    -0.54
    EndContext
    -0.53
    ArgsConstructor
    -0.53
    miste
    -0.51
    doPost
    -0.51
    enumii
    -0.51
     Steg
    -0.50
    GraphicsUnit
    -0.49
     Angleterre
    -0.49
    POSITIVE LOGITS
     REF
    1.13
     refs
    1.01
     ref
    0.95
    REF
    0.95
     useRef
    0.94
     Ref
    0.92
     Refs
    0.92
     references
    0.90
    ref
    0.89
     Reference
    0.87
    Act Density 0.359%

    No Known Activations