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

    Neuronpedia

    INDEX
    Explanations

    self-treating dangers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COMMENTS
    0.44
    тифика
    0.40
     maliciously
    0.40
    વું
    0.39
    தியும்
    0.39
    discos
    0.39
    抿
    0.38
     boobs
    0.38
    хой
    0.37
    বুব
    0.37
    POSITIVE LOGITS
     self
    0.46
     fool
    0.38
    self
    0.38
    自行
    0.37
    Can
    0.37
     kiosk
    0.36
     potentially
    0.35
    safe
    0.34
     গৃহ
    0.34
    等待
    0.34
    Act Density 0.001%

    No Known Activations