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

    Neuronpedia

    INDEX
    Explanations

    few of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ệt
    -0.59
    ">
    -0.56
    '>{
    -0.55
     useStyles
    -0.54
     télécharge
    -0.50
     démocr
    -0.50
     consultato
    -0.50
     désol
    -0.49
    ">{
    -0.49
     reaſon
    -0.49
    POSITIVE LOGITS
     Nevertheless
    0.54
     lucky
    0.54
     individuals
    0.53
    الصفحه
    0.52
     tolerate
    0.51
     OnTriggerEnter
    0.51
     precede
    0.50
     preserve
    0.50
     or
    0.49
     are
    0.49
    Act Density 0.002%

    No Known Activations