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

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hazards
    -0.07
    atient
    -0.07
    レー
    -0.07
    енный
    -0.07
     blot
    -0.06
    279
    -0.06
     dearly
    -0.06
    楽し
    -0.06
     COMPANY
    -0.06
     همه
    -0.06
    POSITIVE LOGITS
    GNUC
    0.06
     구매
    0.06
    isu
    0.06
     strategically
    0.06
    preserve
    0.06
    _gp
    0.06
    Accordion
    0.06
    _AVAILABLE
    0.06
    ��
    0.06
    ục
    0.06
    Act Density 0.033%

    No Known Activations