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

    Neuronpedia

    INDEX
    Explanations

    gelatin or echo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     majest
    0.44
     vorbere
    0.44
    rollen
    0.43
    큽
    0.42
     berg
    0.41
    i
    0.40
    旮
    0.40
     efficacement
    0.40
     distortions
    0.39
     understandings
    0.39
    POSITIVE LOGITS
    CATEGORY
    0.51
     સારી
    0.49
     ম্যানেজার
    0.48
     सामान्य
    0.48
    superclass
    0.47
     સાર
    0.46
     trabajador
    0.46
     районе
    0.46
     时尚
    0.46
     ٻ
    0.44
    Act Density 0.001%

    No Known Activations