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

    Neuronpedia

    INDEX
    Explanations

    consisting of or containing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     వ్యక్
    0.43
     furs
    0.42
     Combo
    0.39
    माही
    0.38
     females
    0.38
     కొంత
    0.38
     descont
    0.37
     combo
    0.37
     Хабаров
    0.36
    jeni
    0.36
    POSITIVE LOGITS
     consisting
    0.99
     consists
    0.91
     terdiri
    0.86
     comprised
    0.83
     comprising
    0.82
     состоит
    0.82
     består
    0.82
     comprises
    0.77
     gồm
    0.76
     containing
    0.75
    Act Density 0.040%

    No Known Activations