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

    Neuronpedia

    INDEX
    Explanations

    health related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fence
    -0.08
     визначення
    -0.06
    ByEmail
    -0.06
    SQ
    -0.06
     BET
    -0.06
    ятий
    -0.06
    tog
    -0.06
    ΟΣ
    -0.06
    emos
    -0.06
    ımın
    -0.06
    POSITIVE LOGITS
     postage
    0.08
    (ALOAD
    0.07
    距
    0.06
    ｝
    0.06
     trem
    0.06
     актив
    0.06
     […
    0.06
     rozum
    0.06
     Arthur
    0.06
    _add
    0.06
    Act Density 0.010%

    No Known Activations