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

    Neuronpedia

    INDEX
    Explanations

    style and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    veg
    0.39
    bog
    0.39
    uxxxx
    0.38
    tort
    0.37
    वें
    0.37
    Soccer
    0.37
    inhos
    0.36
    бота
    0.36
    तिर
    0.35
    姿
    0.35
    POSITIVE LOGITS
     Signific
    0.45
     styles
    0.42
     colour
    0.41
     Self
    0.41
     lj
    0.41
     self
    0.40
     lightness
    0.40
     agnostic
    0.40
     stijl
    0.39
     Ritual
    0.39
    Act Density 0.003%

    No Known Activations