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

    Neuronpedia

    INDEX
    Explanations

    ai url

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Open
    0.41
    openia
    0.38
     Open
    0.38
     OpenAPI
    0.37
    ेयर
    0.37
    리카
    0.37
     xvi
    0.37
    stile
    0.36
     PSR
    0.36
     맨
    0.36
    POSITIVE LOGITS
     hai
    0.43
    ai
    0.41
    Dai
    0.38
     verdict
    0.37
     Singh
    0.36
     Figueroa
    0.36
     Hai
    0.36
     Vai
    0.35
     Dai
    0.35
     mur
    0.35
    Act Density 0.011%

    No Known Activations