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

    Neuronpedia

    INDEX
    Explanations

    guiding towards a goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vish
    0.41
     McK
    0.40
     반갑습니다
    0.40
     Λ
    0.39
     Edwards
    0.38
     McLaughlin
    0.38
     Lyn
    0.38
    idad
    0.37
     Pearson
    0.37
    \},
    0.37
    POSITIVE LOGITS
     towards
    0.82
     toward
    0.82
     terhadap
    0.76
     into
    0.70
    使其
    0.68
    towards
    0.65
     hacia
    0.64
     against
    0.62
     khỏi
    0.59
    Towards
    0.58
    Act Density 0.038%

    No Known Activations