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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Matcher
    -0.07
     دين
    -0.07
    něl
    -0.07
     Clock
    -0.07
     açısından
    -0.06
     Cher
    -0.06
     gb
    -0.06
     наві
    -0.06
    ”.
    -0.06
     Courtesy
    -0.06
    POSITIVE LOGITS
     reasoned
    0.07
     USHORT
    0.07
     constitutes
    0.06
    FUL
    0.06
    updated
    0.06
     防
    0.06
    еред
    0.06
    pled
    0.06
    頃
    0.06
    umed
    0.06
    Act Density 0.007%

    No Known Activations