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

    Neuronpedia

    INDEX
    Explanations

    descriptive completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    splitted
    0.43
     educativa
    0.39
     букмекерлар
    0.39
    dule
    0.39
     అధ్య
    0.38
    检
    0.38
    நிலைய
    0.38
     inaug
    0.38
     конкурс
    0.37
    𝓊
    0.37
    POSITIVE LOGITS
     '/'
    0.49
     vassals
    0.39
    ável
    0.38
     свойств
    0.37
    ('-',
    0.36
    거
    0.36
     scanner
    0.36
    mitters
    0.36
     stuff
    0.36
     سخ
    0.35
    Act Density 0.000%

    No Known Activations