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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.72
     muda
    0.63
     (((
    0.62
     didactic
    0.60
     물리
    0.60
     (-
    0.60
     増
    0.59
     ((
    0.58
    ^{-(
    0.58
     (!
    0.57
    POSITIVE LOGITS
    equivalent
    0.85
    approx
    0.84
    Equivalent
    0.83
    不到
    0.82
    approximately
    0.82
     Equivalent
    0.80
     equivalent
    0.79
    equival
    0.77
     широко
    0.77
    metric
    0.76
    Act Density 0.477%

    No Known Activations