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

    Neuronpedia

    INDEX
    Explanations

    technical concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iba
    0.61
    iken
    0.61
    핸
    0.61
    ovanja
    0.60
    sova
    0.57
     자동으로
    0.55
    izo
    0.54
     titolo
    0.54
    ôme
    0.54
     ribbon
    0.53
    POSITIVE LOGITS
     प्रकाशित
    0.63
    ើម
    0.58
    罒
    0.57
     сё
    0.57
     котором
    0.56
     cuáles
    0.56
    Published
    0.55
     Fidelity
    0.55
    改正
    0.55
     Scare
    0.55
    Act Density 0.000%

    No Known Activations