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

    Neuronpedia

    INDEX
    Explanations

    harm to oneself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಕ್ಷೇತ್ರದಲ್ಲಿ
    0.47
    carrito
    0.45
    Transicao
    0.44
    ಕಾರ
    0.44
    Accessible
    0.43
     ಆಧ
    0.43
    립니다
    0.43
     தேவை
    0.42
    Closeup
    0.41
    разде
    0.41
    POSITIVE LOGITS
     as
    0.43
     Pharmacology
    0.43
     Melissa
    0.42
     executive
    0.41
     As
    0.40
    ع
    0.40
     Angel
    0.39
    anga
    0.39
     Angela
    0.39
    hb
    0.39
    Act Density 0.001%

    No Known Activations