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

    Neuronpedia

    INDEX
    Explanations

    meaning, definition, or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.43
     with
    0.42
     from
    0.40
    Â
    0.40
     destes
    0.39
    D
    0.39
    0
    0.38
    b
    0.37
    ad
    0.37
     Karla
    0.36
    POSITIVE LOGITS
     अर्थात्
    0.52
     అనేది
    0.44
     ifades
    0.41
     అంటే
    0.40
    是什麼
    0.40
     ”,
    0.40
    指的是
    0.39
     എന്നത്
    0.38
     這個
    0.38
    ｣
    0.37
    Act Density 0.113%

    No Known Activations