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

    Neuronpedia

    INDEX
    Explanations

    cutting tool, television licence, microorganisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    服务端
    0.81
     كافة
    0.74
    adto
    0.72
    मित्व
    0.69
     غم
    0.68
     заключа
    0.68
    來看
    0.68
     iż
    0.67
    ؑ
    0.67
     شہادت
    0.66
    POSITIVE LOGITS
     இடை
    0.80
    分页
    0.76
     Alcal
    0.74
     பறி
    0.74
     told
    0.73
     fairer
    0.72
     slic
    0.71
     intensiv
    0.71
     tries
    0.71
     پیسو
    0.70
    Act Density 0.003%

    No Known Activations