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

    Neuronpedia

    INDEX
    Explanations

    carousel, fun, strengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IGR
    0.44
    accommodation
    0.43
     Accommodation
    0.41
    Accommodation
    0.39
    ष्टा
    0.38
    voie
    0.37
    uencias
    0.37
    亿美元
    0.36
     accommodation
    0.35
    localized
    0.35
    POSITIVE LOGITS
     scare
    0.44
     muu
    0.40
    쟈
    0.38
     fuss
    0.38
     baff
    0.38
     wor
    0.37
     zub
    0.36
    τροπ
    0.36
     vortices
    0.36
     kasih
    0.36
    Act Density 0.000%

    No Known Activations