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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    চিক
    0.36
    MakeRect
    0.35
    TrackAngle
    0.33
    WithSize
    0.33
    বিমান
    0.33
    AlignedText
    0.33
    🛖
    0.33
    ScienceStudent
    0.32
     AppCompatTheme
    0.32
    ठमा
    0.32
    POSITIVE LOGITS
     steep
    0.32
    Je
    0.32
     way
    0.31
    case
    0.31
    hora
    0.30
    pure
    0.30
     Dixie
    0.29
    express
    0.29
    Credit
    0.29
    urat
    0.29
    Act Density 0.005%

    No Known Activations