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

    Neuronpedia

    INDEX
    Explanations

    credit and lending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    க்
    0.63
     current
    0.57
     name
    0.57
     privacidad
    0.57
     taş
    0.54
    ↵↵
    0.53
     basics
    0.53
     Çalış
    0.53
     privacy
    0.52
     beliefs
    0.52
    POSITIVE LOGITS
    ‒
    0.65
    го
    0.64
    lemma
    0.63
    поро
    0.61
     კიდ
    0.61
    ৮
    0.61
    Ls
    0.61
    ಾರ್ಟ
    0.61
     почув
    0.61
     lending
    0.61
    Act Density 0.030%

    No Known Activations