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

    Neuronpedia

    INDEX
    Explanations

    forgetfulness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interessieren
    -0.08
     bieten
    -0.08
     atual
    -0.08
     lept
    -0.07
     thrive
    -0.07
    ild
    -0.07
     привести
    -0.07
    Exclusive
    -0.07
    ent
    -0.07
     exclusivement
    -0.07
    POSITIVE LOGITS
     مصنوع
    0.08
    过
    0.08
     Hugo
    0.08
     све
    0.08
    కుండా
    0.07
    מ
    0.07
    ，总
    0.07
    ，好
    0.07
     überhaupt
    0.07
     unsettling
    0.07
    Act Density 0.037%

    No Known Activations