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

    Neuronpedia

    INDEX
    Explanations

    instructions or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pp
    0.37
    オク
    0.36
    én
    0.36
     refrained
    0.36
     rodzaju
    0.36
    isex
    0.34
    setRoi
    0.34
     heavy
    0.33
    boat
    0.33
    cropped
    0.33
    POSITIVE LOGITS
     cohes
    0.46
     ஒரே
    0.44
    Manage
    0.42
     together
    0.41
     একসাথে
    0.39
    昶
    0.39
    拃
    0.39
     Flan
    0.38
    ართველოს
    0.37
    紵
    0.37
    Act Density 0.000%

    No Known Activations