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

    Neuronpedia

    INDEX
    Explanations

    positive feedback and constructive criticism

    oai_token-act-pair · gemini-2.0-flash

    criticism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.75
    onOptions
    -0.73
    expandindo
    -0.60
    libft
    -0.56
    endaftaran
    -0.56
    thaler
    -0.55
    Skocz
    -0.53
     Lindberg
    -0.53
    RegistryLite
    -0.53
    TabLayout
    -0.53
    POSITIVE LOGITS
     criticism
    1.36
     critical
    1.25
    cri
    1.25
     Cri
    1.25
     critique
    1.21
    critical
    1.16
     crítica
    1.13
     Criticism
    1.10
     constructive
    1.10
     critiques
    1.09
    Act Density 1.730%

    No Known Activations