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

    Neuronpedia

    INDEX
    Explanations

    pets above all else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᕈ
    0.41
    吣
    0.39
    rafpunkte
    0.39
    閲覧
    0.39
    ÔNG
    0.38
    Stylish
    0.38
    ourism
    0.37
    ://$
    0.37
    াদেশিক
    0.37
    iint
    0.37
    POSITIVE LOGITS
    لاف
    0.42
     cogn
    0.36
     Xi
    0.36
     тура
    0.36
     cultivators
    0.36
     Mur
    0.35
     végét
    0.35
     Sunshine
    0.35
     стен
    0.35
     उद्या
    0.35
    Act Density 0.000%

    No Known Activations