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

    Neuronpedia

    INDEX
    Explanations

    an AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Artificial
    0.43
     க
    0.38
    artificial
    0.37
     K
    0.37
     Artificial
    0.36
    ச்
    0.36
    ಾಲ
    0.35
    異
    0.35
     mAh
    0.35
     Metast
    0.34
    POSITIVE LOGITS
    ربی
    0.42
     obč
    0.40
    رب
    0.37
    wani
    0.37
     Chirop
    0.37
     hosp
    0.37
     Reece
    0.36
     thawing
    0.36
     autos
    0.36
    versed
    0.36
    Act Density 0.007%

    No Known Activations