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

    Neuronpedia

    INDEX
    Explanations

    conclusion restate thesis summarize surveys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    跏
    0.43
    ницей
    0.41
    symplectic
    0.40
    ⺈
    0.39
    VSLU
    0.38
     नाखून
    0.38
    रुख
    0.37
    idopsis
    0.37
    тельной
    0.37
    რების
    0.36
    POSITIVE LOGITS
     So
    0.44
     No
    0.44
     Click
    0.43
     С
    0.41
     For
    0.41
     Download
    0.41
     H
    0.41
     Link
    0.41
    download
    0.41
    CLICK
    0.40
    Act Density 0.001%

    No Known Activations