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

    Neuronpedia

    INDEX
    Explanations

    discussions and topics related to community and collaboration

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

    discussing topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.57
    rungsseite
    -0.56
     esternos
    -0.56
    WithIOException
    -0.54
    énieur
    -0.52
    SBATCH
    -0.52
    jspb
    -0.52
    enderror
    -0.52
    DispatchToProps
    -0.51
    oredCriteria
    -0.51
    POSITIVE LOGITS
     how
    0.48
     strategies
    0.46
     various
    0.45
     the
    0.45
     global
    0.41
     evaluating
    0.39
     different
    0.38
     discussing
    0.37
    adaptiveStyles
    0.37
     about
    0.36
    Act Density 0.019%

    No Known Activations