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

    Neuronpedia

    INDEX
    Explanations

    acknowledgment and readiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.28
     retarded
    0.25
     luminous
    0.25
     virkelig
    0.24
     ඔබේ
    0.24
     vaš
    0.24
    }--\
    0.24
     delineated
    0.24
    မဲ့
    0.24
     fungal
    0.24
    POSITIVE LOGITS
     Oh
    0.45
     oh
    0.44
    Oh
    0.40
    oh
    0.39
     ah
    0.37
     Ah
    0.37
     Excellent
    0.37
    哦
    0.37
    Excellent
    0.36
     excellent
    0.36
    Act Density 0.180%

    No Known Activations