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

    Neuronpedia

    INDEX
    Explanations

    alternative spellings or transliterations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overall
    0.41
    upa
    0.41
    la
    0.40
    particularly
    0.40
    ate
    0.39
    avy
    0.39
    ement
    0.38
    j
    0.38
    if
    0.38
     Tre
    0.38
    POSITIVE LOGITS
     logLevel
    0.48
    娍
    0.44
    䔬
    0.43
    家长
    0.43
     термина
    0.41
     playroom
    0.41
    更改
    0.41
     হ্রাস
    0.40
     大人
    0.39
     फंडिंग
    0.39
    Act Density 0.001%

    No Known Activations