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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion and emotional reactions

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

    incorrect guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.65
     المعيارى
    -0.54
    wiſe
    -0.54
     teething
    -0.51
    Біографія
    -0.50
    ありました
    -0.50
     navideños
    -0.50
    fficio
    -0.49
    SourceChecksum
    -0.48
    tagext
    -0.48
    POSITIVE LOGITS
     setw
    0.31
     pinulongan
    0.31
    PropertyChanging
    0.30
    ="@+
    0.29
    CORBA
    0.28
     Scalars
    0.28
    олові
    0.28
     <>",
    0.28
    ATS
    0.28
    SCO
    0.28
    Act Density 0.029%

    No Known Activations