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

    Neuronpedia

    INDEX
    Explanations

    exact matches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     params
    0.50
     Parameters
    0.44
     Elements
    0.42
    誰
    0.42
     단
    0.41
     गुंतवण
    0.41
    𝓲
    0.40
     parameters
    0.39
    params
    0.38
    টন
    0.38
    POSITIVE LOGITS
    $=
    0.47
    true
    0.47
    _=
    0.46
     sensitive
    0.42
     true
    0.41
     path
    0.41
    TRUE
    0.40
     TRUE
    0.40
     sensitivity
    0.38
    sensitive
    0.38
    Act Density 0.000%

    No Known Activations