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

    Neuronpedia

    INDEX
    Explanations

    File paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jose
    -0.07
     mel
    -0.07
    副秘书长
    -0.07
    amedi
    -0.07
     pou
    -0.06
    .JPanel
    -0.06
    Bs
    -0.06
    ضرب
    -0.06
     Claude
    -0.06
    不失
    -0.06
    POSITIVE LOGITS
     phosphate
    0.07
    ilog
    0.07
    .Entry
    0.07
     Fragment
    0.07
     הג
    0.07
     אזר
    0.07
    _FACTOR
    0.07
    -url
    0.07
    paragraph
    0.06
    erer
    0.06
    Act Density 0.003%

    No Known Activations