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

    Neuronpedia

    INDEX
    Explanations

    strings of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SF
    -0.68
     F
    -0.57
    fer
    -0.56
    ↵
    -0.54
    A
    -0.54
     te
    -0.54
     
    -0.54
     Me
    -0.53
    fh
    -0.53
    "
    -0.53
    POSITIVE LOGITS
    abestanden
    0.89
     Paglinawan
    0.82
    ſelves
    0.79
     onCancelled
    0.78
    __(/*!
    0.77
    setVerticalGroup
    0.76
     Efq
    0.76
     itſelf
    0.75
     photolibrary
    0.75
     numberWith
    0.73
    Act Density 0.262%

    No Known Activations