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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Xna
    -0.56
     betweenstory
    -0.54
    abbix
    -0.53
     adelante
    -0.50
     oprot
    -0.50
    uchtigkeit
    -0.50
     PWN
    -0.49
    ObjectContext
    -0.48
    jš
    -0.48
    :✨
    -0.48
    POSITIVE LOGITS
    
    0.54
    downe
    0.49
    BeginContext
    0.49
    niająca
    0.47
    RotationOrder
    0.46
    tru
    0.44
     kasarigan
    0.43
     account
    0.43
     transfieras
    0.43
     Exacts
    0.42
    Act Density 0.000%

    No Known Activations