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

    Neuronpedia

    INDEX
    Explanations

    list enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    piej
    0.42
    蛲
    0.41
    物质
    0.40
    瓤
    0.40
    耱
    0.40
    Durham
    0.39
    藜
    0.39
    রোগ
    0.39
    激素
    0.39
    土壤
    0.38
    POSITIVE LOGITS
     kecuali
    0.42
    -
    0.39
     D
    0.36
    ,
    0.34
    basi
    0.33
     Este
    0.33
     unimportant
    0.32
     incriminating
    0.32
     It
    0.32
     alias
    0.32
    Act Density 0.001%

    No Known Activations