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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DRIVE
    -0.06
    etr
    -0.06
    SECOND
    -0.06
    _sg
    -0.06
     Kiş
    -0.06
    representation
    -0.06
     Wet
    -0.06
     systematically
    -0.06
    اصله
    -0.06
    ropa
    -0.06
    POSITIVE LOGITS
     �
    0.07
     αγ
    0.07
     proud
    0.06
     منطقة
    0.06
    ('-
    0.06
    :param
    0.06
     ideological
    0.06
     При
    0.06
     infos
    0.06
     заболевания
    0.06
    Act Density 0.001%

    No Known Activations