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

    Neuronpedia

    INDEX
    Explanations

    commands and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bashing
    0.82
    openia
    0.75
     souten
    0.75
     avevano
    0.72
    issi
    0.70
    yan
    0.68
     создании
    0.68
     observant
    0.68
     bess
    0.68
     suisse
    0.67
    POSITIVE LOGITS
     کردن
    1.54
    able
    1.48
     operation
    1.33
     All
    1.27
    All
    1.26
    方法
    1.24
     Operation
    1.18
    all
    1.16
     method
    1.13
    された
    1.12
    Act Density 0.376%

    No Known Activations