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

    Neuronpedia

    INDEX
    Explanations

    words that describe behavior or qualities negatively

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LEYENDO
    -0.59
     ModelRenderer
    -0.57
    ParallelGroup
    -0.57
     testified
    -0.54
    DataAnnotations
    -0.54
     testify
    -0.54
    setupUi
    -0.54
    Erstellt
    -0.53
     ElementRef
    -0.52
     typelib
    -0.52
    POSITIVE LOGITS
     nonchal
    0.70
    Poloha
    0.63
     carelessly
    0.60
     remarks
    0.59
     cavalier
    0.58
     sarcastic
    0.58
     careless
    0.58
     comments
    0.55
     shrug
    0.55
     herab
    0.55
    Act Density 1.029%

    No Known Activations