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

    Neuronpedia

    INDEX
    Explanations

    9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phys
    0.42
     physiological
    0.40
     outings
    0.38
    esent
    0.38
    যেন
    0.38
     stiffer
    0.37
     ports
    0.37
     endgame
    0.36
     phys
    0.36
    sizes
    0.36
    POSITIVE LOGITS
    实行
    0.41
    ʿ
    0.39
    ѝ
    0.34
     Belediye
    0.33
    Donald
    0.33
     Hat
    0.32
     νε
    0.32
     బోర్
    0.32
    樾
    0.32
     அவருடைய
    0.32
    Act Density 0.005%

    No Known Activations