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

    Neuronpedia

    INDEX
    Explanations

    price list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     detection
    0.43
     hypertext
    0.41
     ref
    0.41
     stimuli
    0.40
     transcoding
    0.40
     unexpected
    0.40
     static
    0.39
     object
    0.37
     detectable
    0.36
    拼
    0.36
    POSITIVE LOGITS
     enthous
    0.58
    nYou
    0.57
    nThe
    0.56
    घरों
    0.55
    ®,
    0.54
    czeniu
    0.54
    ට්
    0.54
    ނީ
    0.53
     परियोजनाओं
    0.53
    euros
    0.53
    Act Density 0.506%

    No Known Activations