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

    Neuronpedia

    INDEX
    Explanations

    toilet paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `
    0.46
     bathroom
    0.42
     din
    0.42
     verlassen
    0.42
     *
    0.40
     work
    0.40
     disable
    0.39
     Wide
    0.39
    religious
    0.39
     religious
    0.39
    POSITIVE LOGITS
    Brush
    0.47
    Paper
    0.45
     PAPER
    0.44
    CEP
    0.41
    几
    0.41
    스템
    0.40
    ISES
    0.39
    台上
    0.39
    需
    0.39
    FORMAN
    0.39
    Act Density 0.014%

    No Known Activations