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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    äßig
    -0.07
    PCODE
    -0.07
    (Current
    -0.07
     UIBar
    -0.07
    queryString
    -0.07
    $x
    -0.07
    红外
    -0.06
    _mes
    -0.06
     순
    -0.06
    מדה
    -0.06
    POSITIVE LOGITS
    潜在
    0.07
    _UNLOCK
    0.07
    本质
    0.06
    账户
    0.06
    arendra
    0.06
    _fake
    0.06
    .tool
    0.06
    LB
    0.06
    实体经济
    0.06
    -light
    0.06
    Act Density 0.007%

    No Known Activations