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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亗
    0.51
    KILL
    0.47
     fraîche
    0.47
    Tier
    0.46
    棪
    0.46
     leichter
    0.45
    কে
    0.44
    Poll
    0.43
    Crown
    0.43
     faisait
    0.43
    POSITIVE LOGITS
    ik
    0.62
     aficionados
    0.58
     ebooks
    0.55
     books
    0.53
     singers
    0.53
    á
    0.53
     comedians
    0.52
     arrhythmia
    0.52
    oc
    0.52
     dancers
    0.52
    Act Density 0.000%

    No Known Activations