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

    Neuronpedia

    INDEX
    Explanations

    business and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hangar
    0.40
    alled
    0.39
     Nike
    0.39
     Johnny
    0.38
     booming
    0.38
     Drake
    0.37
     handles
    0.37
    ikus
    0.37
     Popular
    0.36
    ialis
    0.36
    POSITIVE LOGITS
    ментов
    0.41
    zymy
    0.40
     aziende
    0.39
     dicion
    0.39
    ประก
    0.38
     poslov
    0.38
     ramo
    0.38
    感谢
    0.38
     entreprises
    0.37
    ㄻ
    0.37
    Act Density 0.000%

    No Known Activations