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

    Neuronpedia

    INDEX
    Explanations

    code defining models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fscanf
    0.41
    ﹰ
    0.39
     suyo
    0.38
    进度
    0.38
    म्पियन
    0.38
    进
    0.37
    久
    0.36
    넝
    0.36
     illuminating
    0.36
     ventilated
    0.36
    POSITIVE LOGITS
    models
    0.59
     models
    0.55
    Models
    0.54
     Models
    0.54
     MODELS
    0.49
     model
    0.43
    model
    0.43
     модели
    0.43
    backends
    0.42
    Model
    0.41
    Act Density 0.001%

    No Known Activations