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

    Neuronpedia

    INDEX
    Explanations

    C# code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zasad
    0.43
     Приступ
    0.42
     ornamented
    0.38
     Wege
    0.37
    faz
    0.37
    ρύ
    0.37
     பரி
    0.37
     erecting
    0.37
    ້າງ
    0.37
     Ashraf
    0.37
    POSITIVE LOGITS
     solved
    0.42
    Match
    0.41
    itions
    0.41
    solved
    0.40
    ving
    0.39
    ying
    0.37
    Matching
    0.37
    match
    0.37
    matching
    0.37
    ctions
    0.36
    Act Density 0.000%

    No Known Activations