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

    Neuronpedia

    INDEX
    Explanations

    exception handling or legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gruppe
    1.59
    gruppen
    1.49
    리
    1.41
    та
    1.40
    ედერ
    1.36
    ح
    1.30
     établir
    1.29
    경제
    1.28
     percentuale
    1.28
     thérapeut
    1.27
    POSITIVE LOGITS
     are
    1.59
     is
    1.55
     can
    1.49
     was
    1.44
     were
    1.37
     will
    1.34
     hostilities
    1.30
     in
    1.28
    この
    1.27
     D
    1.27
    Act Density 0.001%

    No Known Activations