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

    Neuronpedia

    INDEX
    Explanations

    me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Veil
    0.40
    Estab
    0.40
    Пол
    0.39
     coinvol
    0.38
    brushes
    0.37
     Mannschaft
    0.36
    瞭
    0.36
     Unwrap
    0.36
     Bridges
    0.36
     oggetto
    0.36
    POSITIVE LOGITS
    шие
    0.43
     PREMIUM
    0.39
    urous
    0.38
    itian
    0.37
    stool
    0.37
     말미
    0.37
     premium
    0.36
    izi
    0.36
    페이지
    0.36
    編集
    0.36
    Act Density 0.000%

    No Known Activations