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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _theta
    -0.07
    mediately
    -0.06
    _kel
    -0.06
    =pos
    -0.06
    绝
    -0.06
    显
    -0.06
     cực
    -0.06
    字
    -0.06
    ICO
    -0.06
    lm
    -0.06
    POSITIVE LOGITS
    release
    0.07
     mont
    0.07
    redi
    0.07
    Preference
    0.07
    )value
    0.06
    (iterator
    0.06
    _create
    0.06
     forgiveness
    0.06
    ale
    0.06
    $params
    0.06
    Act Density 0.020%

    No Known Activations