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

    Neuronpedia

    INDEX
    Explanations

    software errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    察
    -0.07
     Warren
    -0.06
    962
    -0.06
     ul
    -0.06
    ｛
    -0.06
    Fraction
    -0.06
    _credentials
    -0.06
    producto
    -0.06
    θενής
    -0.06
     frags
    -0.06
    POSITIVE LOGITS
     کردن
    0.07
     halted
    0.06
    toString
    0.06
     timing
    0.06
    thern
    0.06
    >'+↵
    0.06
    /slider
    0.06
    slider
    0.06
     vaginal
    0.06
     vol
    0.06
    Act Density 0.021%

    No Known Activations