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

    Neuronpedia

    INDEX
    Explanations

    conversational turns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fabrication
    1.21
     curing
    1.13
     encoding
    1.12
     encoded
    1.11
     carving
    1.11
     artisans
    1.08
     assemblage
    1.07
     weaving
    1.07
     harvesting
    1.06
     epoca
    1.06
    POSITIVE LOGITS
    \]
    0.83
    ?’
    0.76
    ?»
    0.75
    Because
    0.73
    Take
    0.73
    ».
    0.73
    íč
    0.71
    If
    0.71
     نمی‌
    0.70
    !,
    0.70
    Act Density 0.000%

    No Known Activations