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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可能性がある
    0.62
     polycrystalline
    0.61
    कर
    0.57
    Interaction
    0.57
    0.57
     EventEmitter
    0.56
    gono
    0.56
    眯
    0.56
     indirectly
    0.56
    ඤ
    0.55
    POSITIVE LOGITS
     //
    0.81
    表的
    0.69
     deaktiv
    0.63
     //'
    0.63
     deletes
    0.62
     Birth
    0.62
     due
    0.61
     করিতেন
    0.61
     fut
    0.60
     指
    0.60
    Act Density 0.088%

    No Known Activations