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

    Neuronpedia

    INDEX
    Explanations

    positive news or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ባቸው
    0.41
     fours
    0.38
    ᖕ
    0.38
     keel
    0.37
    كال
    0.37
     ഹിന്ദ
    0.37
     luxe
    0.36
    idas
    0.36
     burs
    0.36
     foreach
    0.36
    POSITIVE LOGITS
     dietro
    0.48
     detrás
    0.47
     Jamb
    0.39
     behind
    0.38
    ٰی
    0.36
     isotonic
    0.36
    ęk
    0.36
     godziny
    0.36
    etan
    0.35
    '};
    0.35
    Act Density 0.000%

    No Known Activations