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

    Neuronpedia

    INDEX
    Explanations

    your or user related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ండ్లు
    0.53
    ản
    0.50
     ಔ
    0.50
    []');
    0.50
    )}^{\
    0.49
    jasama
    0.49
    ಿಸಿದ್ದರು
    0.49
    nbhd
    0.49
    ischen
    0.49
    ́a
    0.49
    POSITIVE LOGITS
    方法
    0.54
    0.52
    The
    0.51
    。
    0.50
    ：
    0.50
    Res
    0.48
    You
    0.48
    Does
    0.47
    （
    0.47
    Measurements
    0.46
    Act Density 0.000%

    No Known Activations