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

    Neuronpedia

    INDEX
    Explanations

    identifies common objects, dislikes disrespect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ərə
    0.49
     altres
    0.47
     antioxidants
    0.47
     bırak
    0.47
     estratégia
    0.46
     éve
    0.46
     ajouter
    0.44
     príncipe
    0.44
     antidepressants
    0.44
     combines
    0.44
    POSITIVE LOGITS
    3
    0.51
    TT
    0.50
    text
    0.49
    ф
    0.49
    TH
    0.48
    FT
    0.48
    bullet
    0.47
    pt
    0.47
    mortem
    0.46
    頂
    0.46
    Act Density 0.001%

    No Known Activations