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

    Neuronpedia

    INDEX
    Explanations

    prediction and warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.27
     sawtooth
    0.27
     B
    0.27
     framebuffer
    0.27
     Neue
    0.26
     Bl
    0.26
    3
    0.26
     adicionales
    0.25
     S
    0.25
     teeming
    0.25
    POSITIVE LOGITS
    決して
    0.29
    OpportunitiesBy
    0.29
     unlawfully
    0.28
     økonom
    0.27
    లేదు
    0.27
     prostit
    0.27
     unlaw
    0.26
     unwittingly
    0.26
     بلکہ
    0.26
     иностран
    0.26
    Act Density 0.000%

    No Known Activations