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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COMMAND
    -0.07
     prest
    -0.06
    -state
    -0.06
     accents
    -0.06
    _ent
    -0.06
     Ze
    -0.06
    -powered
    -0.06
    pection
    -0.06
    leetcode
    -0.06
     hwnd
    -0.06
    POSITIVE LOGITS
     achieved
    0.07
    ело
    0.07
    ARED
    0.07
     campos
    0.07
    امه
    0.06
    ulin
    0.06
    ilin
    0.06
     بگ
    0.06
     enhances
    0.06
    俗
    0.06
    Act Density 0.000%

    No Known Activations