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

    Neuronpedia

    INDEX
    Explanations

    observation phase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odynam
    0.47
    มากมาย
    0.43
    punkt
    0.42
    gF
    0.41
    KBr
    0.41
    ələ
    0.41
    ourier
    0.40
    บร
    0.40
    ogliere
    0.39
    ấc
    0.39
    POSITIVE LOGITS
     Below
    0.45
    如下
    0.44
     Ethan
    0.43
     incluye
    0.42
     Richard
    0.42
     voici
    0.41
     Cour
    0.40
     inclui
    0.39
     ಪ್ರದೇಶ
    0.39
     below
    0.39
    Act Density 0.000%

    No Known Activations