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

    Neuronpedia

    INDEX
    Explanations

    launchpads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.61
    ion
    0.55
    ber
    0.55
    d
    0.54
    k
    0.54
    л
    0.53
    élev
    0.52
    z
    0.52
    م
    0.52
    속
    0.49
    POSITIVE LOGITS
    気軽に
    0.50
     TECHNICAL
    0.48
    ིག་
    0.48
     TAN
    0.47
     Botanical
    0.47
     teknik
    0.46
     Smoke
    0.46
     MALL
    0.46
    юн
    0.46
     homozygous
    0.46
    Act Density 0.000%

    No Known Activations