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

    Neuronpedia

    INDEX
    Explanations

    daily

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    しか
    -0.07
    Jun
    -0.07
    ลง
    -0.07
     Romantic
    -0.07
    ertext
    -0.07
    みな
    -0.07
    并于
    -0.07
    sequently
    -0.07
    _transaction
    -0.06
    ises
    -0.06
    POSITIVE LOGITS
    irk
    0.07
     remarks
    0.07
    мет
    0.07
     debris
    0.07
     dimensions
    0.07
     zones
    0.06
     pc
    0.06
    斡
    0.06
     ref
    0.06
     FP
    0.06
    Act Density 0.058%

    No Known Activations