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

    Neuronpedia

    INDEX
    Explanations

    numbers, ordered, gauge, trigger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ubes
    0.67
     nit
    0.67
     widers
    0.66
     constitutive
    0.63
    kans
    0.62
     instances
    0.61
     vors
    0.61
     الخامس
    0.61
     henüz
    0.60
    プション
    0.60
    POSITIVE LOGITS
     Charlotte
    0.82
    ฀
    0.78
    రు
    0.77
    ޯ
    0.77
     DEJ
    0.76
    </h6>
    0.73
    øre
    0.73
    Ɵ
    0.73
     Reakt
    0.73
     Tensorflow
    0.71
    Act Density 0.001%

    No Known Activations