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

    Neuronpedia

    INDEX
    Explanations

    qualifiers, definitions, probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ダウン
    0.42
    ]."
    0.42
    abilis
    0.41
     Ihren
    0.41
     Mata
    0.41
     whichever
    0.40
    ”।
    0.39
     Allgemeinen
    0.39
    」。
    0.39
    ’।
    0.39
    POSITIVE LOGITS
     remains
    0.42
     exact
    0.41
     is
    0.41
    真正
    0.40
    实在是
    0.39
    성은
    0.39
    ரமாக
    0.38
    തല്ല
    0.38
     requisite
    0.38
    するのは
    0.38
    Act Density 0.194%

    No Known Activations