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

    Neuronpedia

    INDEX
    Explanations

    hex code #f0f0f0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ovipares
    0.38
     Ztg
    0.36
     eluted
    0.36
     adsorbed
    0.35
    Peq
    0.34
    షు
    0.33
    Elater
    0.33
    舂
    0.33
    丵
    0.33
    मस्कार
    0.33
    POSITIVE LOGITS
    ё
    0.39
     aan
    0.38
     Thành
    0.37
     new
    0.36
    Text
    0.36
     कलर
    0.36
     é
    0.35
    new
    0.35
     pode
    0.35
     Text
    0.35
    Act Density 0.007%

    No Known Activations