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

    Neuronpedia

    INDEX
    Explanations

    learning from experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blackmail
    0.45
     intravenous
    0.41
     biasing
    0.40
     hypothetical
    0.39
     wry
    0.38
     overkill
    0.38
     chandelier
    0.38
     extrapolation
    0.38
     intentar
    0.38
     dodgy
    0.38
    POSITIVE LOGITS
     жизни
    0.44
    üler
    0.42
     चुनौतियों
    0.41
    Leadership
    0.40
    𝘦
    0.39
    зульта
    0.39
    และ
    0.38
     увлека
    0.38
    充满
    0.38
    行为
    0.38
    Act Density 0.236%

    No Known Activations