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

    Neuronpedia

    INDEX
    Explanations

    numbers with units or in calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordinal
    0.53
     ASCII
    0.51
     orchestr
    0.49
     jad
    0.48
     heist
    0.46
     TypeScript
    0.46
     lifespan
    0.46
     coexistence
    0.45
     dutiful
    0.45
     chore
    0.45
    POSITIVE LOGITS
    8
    0.82
    7
    0.79
    6
    0.77
    5
    0.77
    2
    0.74
    9
    0.72
    1
    0.68
    3
    0.66
    4
    0.65
    0
    0.55
    Act Density 0.444%

    No Known Activations