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

    Neuronpedia

    INDEX
    Explanations

    objects and their states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     доку
    0.44
     rodi
    0.43
    posti
    0.42
     электро
    0.41
    ikhil
    0.40
    ৃক
    0.39
     зеле
    0.38
    вяза
    0.38
     озе
    0.38
    グリーン
    0.37
    POSITIVE LOGITS
     Models
    0.40
     Mensch
    0.39
    模型
    0.39
    Models
    0.38
    䚺
    0.38
     Modelo
    0.37
    MaxSize
    0.37
    മെ
    0.37
    矵
    0.36
     smokes
    0.36
    Act Density 0.001%

    No Known Activations