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

    Neuronpedia

    INDEX
    Explanations

    call me or call to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yre
    0.52
    yya
    0.44
    ueness
    0.42
    reiber
    0.41
    yf
    0.41
    тове
    0.41
    routingHeader
    0.40
    खिक
    0.40
    ኪያ
    0.40
    gué
    0.39
    POSITIVE LOGITS
     upon
    0.90
     call
    0.70
     forth
    0.67
    Upon
    0.66
    Call
    0.65
    upon
    0.65
     Call
    0.60
    call
    0.59
     Upon
    0.59
    Calling
    0.58
    Act Density 0.022%

    No Known Activations