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

    Neuronpedia

    INDEX
    Explanations

    Phone/tech articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肱
    -0.07
     Highest
    -0.07
     mein
    -0.07
    最初的
    -0.07
    _cp
    -0.07
    .userInfo
    -0.07
    הפך
    -0.06
    莸
    -0.06
    fter
    -0.06
     primeira
    -0.06
    POSITIVE LOGITS
    Overlay
    0.08
    -Shirt
    0.07
    מניע
    0.07
    guards
    0.07
    vier
    0.06
    ושא
    0.06
    mvc
    0.06
    .initialize
    0.06
     Polynomial
    0.06
    \Plugin
    0.06
    Act Density 0.051%

    No Known Activations