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

    Neuronpedia

    INDEX
    Explanations

    travel advice and hydration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devient
    0.49
     دي
    0.48
     מה
    0.47
     Teut
    0.47
     עם
    0.47
     jut
    0.46
     ယ
    0.46
     fed
    0.45
     ponctu
    0.45
     být
    0.45
    POSITIVE LOGITS
    ह
    0.44
    द
    0.43
    ools
    0.43
    )".
    0.43
    .),
    0.42
    сть
    0.42
    uspended
    0.42
    deserved
    0.40
    .'),
    0.40
    νομα
    0.40
    Act Density 0.000%

    No Known Activations