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

    Neuronpedia

    INDEX
    Explanations

    patterns after words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Runner
    0.54
     Continuity
    0.53
     Mike
    0.52
     Koss
    0.51
     Wells
    0.50
     указыва
    0.49
     Rachael
    0.49
     Wire
    0.48
     Resilience
    0.48
     Feature
    0.48
    POSITIVE LOGITS
    {
    0.50
    .
    0.49
     pseudonym
    0.46
    erenza
    0.45
    aisen
    0.45
    städter
    0.45
    :
    0.45
    ="
    0.44
    ush
    0.44
     धोने
    0.44
    Act Density 0.000%

    No Known Activations