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

    Neuronpedia

    INDEX
    Explanations

    astonishing, impressive, regretful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Emm
    0.49
     Z
    0.48
     Variant
    0.48
     मॉडल
    0.47
     ANN
    0.47
    光学
    0.46
     Cov
    0.46
     Sigma
    0.46
     Cess
    0.45
     R
    0.45
    POSITIVE LOGITS
    im
    0.53
    in
    0.52
     interesse
    0.52
    ophiles
    0.52
    eliac
    0.51
    olyte
    0.51
    ow
    0.48
    obtenir
    0.48
    impossible
    0.47
    م
    0.47
    Act Density 0.000%

    No Known Activations