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

    Neuronpedia

    INDEX
    Explanations

    services and inertia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flies
    0.48
     can
    0.47
     were
    0.44
    ]
    0.44
     Konz
    0.44
     operates
    0.43
    xC
    0.43
    }
    0.42
     be
    0.41
    (`
    0.40
    POSITIVE LOGITS
     உதார
    0.44
    util
    0.42
     ચૂક
    0.41
     отказыва
    0.41
    𝗛
    0.41
    ン
    0.41
     போராட்ட
    0.41
     slowing
    0.40
     назвал
    0.40
     ચૂ
    0.40
    Act Density 0.001%

    No Known Activations