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

    Neuronpedia

    INDEX
    Explanations

    early retrieval leading DFT crucial access useful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bath
    0.47
    ellipse
    0.47
    section
    0.46
    dateTime
    0.45
    getValue
    0.45
    त्व
    0.45
    वेश
    0.45
    とな
    0.44
    ơi
    0.44
    ở
    0.44
    POSITIVE LOGITS
    манов
    0.49
    ాలా
    0.47
    裸
    0.46
     Dav
    0.45
    乐
    0.44
     innovative
    0.44
     Renal
    0.44
     Nov
    0.43
     static
    0.43
     nv
    0.43
    Act Density 0.000%

    No Known Activations