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

    Neuronpedia

    INDEX
    Explanations

    holding, secure, bound

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seven
    1.13
    Seven
    1.10
     seven
    1.03
    七
    0.97
     tujuh
    0.95
    7
    0.91
    seven
    0.91
     sieben
    0.88
    सात
    0.87
    ⑦
    0.86
    POSITIVE LOGITS
    ிகி
    0.74
     firm
    0.69
    logn
    0.69
     Signore
    0.68
    EtOH
    0.68
     firmer
    0.67
     Disorders
    0.67
     REPUBLIC
    0.67
    NaClO
    0.66
     securing
    0.65
    Act Density 0.115%

    No Known Activations