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

    Neuronpedia

    INDEX
    Explanations

    html closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    棺
    0.42
     centrality
    0.41
     위해서는
    0.41
     timeliness
    0.39
    ッション
    0.39
     monotonicity
    0.39
     centímetros
    0.39
    🤶
    0.38
    舝
    0.38
     mjest
    0.38
    POSITIVE LOGITS
    bera
    0.40
     e
    0.39
    ኸ
    0.37
     opnieuw
    0.36
     Alegre
    0.36
    ಂತ
    0.36
    META
    0.35
     HE
    0.35
     diper
    0.34
    પ્ર
    0.34
    Act Density 0.028%

    No Known Activations