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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    718
    -0.07
    обов
    -0.06
     Georgia
    -0.06
    modx
    -0.06
    否
    -0.06
    規
    -0.06
     کود
    -0.06
     GetUser
    -0.06
    �
    -0.06
     opioids
    -0.06
    POSITIVE LOGITS
    stru
    0.08
    _gift
    0.07
    plier
    0.07
    ’d
    0.06
    畫
    0.06
    emap
    0.06
     columna
    0.06
     kém
    0.06
    Same
    0.06
     renowned
    0.06
    Act Density 0.298%

    No Known Activations