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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.85
     kaynağından
    -0.82
    -0.81
     itſelf
    -0.79
    JspWriter
    -0.79
     useAppContext
    -0.79
     avoient
    -0.78
     ModelExpression
    -0.78
    ngOnInit
    -0.75
    Geplaatst
    -0.74
    POSITIVE LOGITS
     equ
    0.48
     ab
    0.46
    .
    0.44
     final
    0.44
     R
    0.43
     unknown
    0.42
     LO
    0.42
    <eos>
    0.41
     Love
    0.41
     id
    0.41
    Act Density 0.001%

    No Known Activations