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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express opinions or subjective evaluations about something

    oai_token-act-pair · gemini-2.0-flash

    French words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.29
     defaultstate
    -0.20
    netbeans
    -0.15
    SuppressLint
    -0.14
    Tikang
    -0.14
    UnusedPrivate
    -0.11
     MotionEvent
    -0.10
    roek
    -0.09
    IntoConstraints
    -0.08
     MainAxisSize
    -0.07
    POSITIVE LOGITS
     zijne
    0.97
     vectorielles
    0.96
     avoient
    0.95
     étoient
    0.93
     étoit
    0.89
     feroit
    0.88
     mijne
    0.87
     scolaires
    0.85
     démocr
    0.85
     auroit
    0.85
    Act Density 4.523%

    No Known Activations