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

    Neuronpedia

    INDEX
    Explanations

    macro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drill
    -0.06
    .find
    -0.06
     Volt
    -0.06
     Pitch
    -0.06
    _probs
    -0.06
    _pan
    -0.06
     pel
    -0.06
     ledger
    -0.06
     الکترون
    -0.06
     Winner
    -0.06
    POSITIVE LOGITS
     obsahuje
    0.07
    游戏
    0.07
    Leaf
    0.07
     realizing
    0.06
     jedem
    0.06
    대표
    0.06
     "^
    0.06
    ائل
    0.06
     vých
    0.06
     retir
    0.06
    Act Density 0.002%

    No Known Activations