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

    Neuronpedia

    INDEX
    Explanations

    Use these words in #phrase_list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schedule
    0.44
    輋
    0.44
     Split
    0.43
    萼
    0.43
    ட்சிய
    0.42
     Gardening
    0.42
    筒
    0.42
    㐄
    0.42
     Client
    0.42
     Calend
    0.41
    POSITIVE LOGITS
    л
    0.55
     legitimate
    0.46
    ian
    0.45
     DEPENDENCIA
    0.44
     a
    0.43
    receipt
    0.42
     peligros
    0.42
     які
    0.42
    ми
    0.41
    arious
    0.41
    Act Density 0.005%

    No Known Activations