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

    Neuronpedia

    INDEX
    Explanations

    os module interaction errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ançon
    0.40
     Code
    0.38
    Quiet
    0.38
    تيب
    0.38
     finger
    0.37
    mermaid
    0.37
    thumb
    0.37
     beg
    0.37
     Thumb
    0.37
    Thumb
    0.36
    POSITIVE LOGITS
     OSError
    0.65
    OSE
    0.59
    Os
    0.53
     Os
    0.52
     os
    0.49
     OS
    0.48
     Osborn
    0.47
    sonaro
    0.45
     الوس
    0.44
     Ос
    0.44
    Act Density 0.009%

    No Known Activations