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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qing
    -0.06
    _FRAME
    -0.06
    xffffff
    -0.06
    _IMETHOD
    -0.06
    하면서
    -0.06
    ersen
    -0.06
    ощи
    -0.06
    ilate
    -0.06
    ibble
    -0.06
     thương
    -0.06
    POSITIVE LOGITS
     albeit
    0.07
    Mode
    0.07
     counterparts
    0.07
     accommodations
    0.06
    -rise
    0.06
    melon
    0.06
     outlines
    0.06
     cri
    0.06
     Р
    0.06
    Captain
    0.06
    Act Density 0.000%

    No Known Activations