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

    Neuronpedia

    INDEX
    Explanations

    causes and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]。
    0.68
     }}$.
    0.65
    Trả
    0.63
    ]$.
    0.63
    }$.
    0.62
    если
    0.62
    തെന്നും
    0.61
    Kemudian
    0.61
    NavigationView
    0.60
    )$.
    0.60
    POSITIVE LOGITS
     allows
    1.66
     makes
    1.66
     creates
    1.62
     ensures
    1.61
     gives
    1.59
     brings
    1.58
     enables
    1.47
     implies
    1.46
     proves
    1.44
     undermines
    1.42
    Act Density 0.758%

    No Known Activations