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

    Neuronpedia

    INDEX
    Explanations

    explain concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.46
     आइट
    0.46
    eneuve
    0.45
    nge
    0.45
     ንጥረ
    0.44
    ergy
    0.44
     Giveen
    0.43
     लगेंगे
    0.43
    識
    0.42
     Biết
    0.41
    POSITIVE LOGITS
     workman
    0.45
     dear
    0.44
    มอ
    0.43
     kiel
    0.42
    мам
    0.41
     caro
    0.41
     incomple
    0.40
    fashion
    0.40
    fashioned
    0.40
     batal
    0.39
    Act Density 0.001%

    No Known Activations