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

    Neuronpedia

    INDEX
    Explanations

    selection from a group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ুরুর
    0.40
    ształ
    0.36
     கதை
    0.36
     イヤ
    0.36
     சி
    0.36
    сер
    0.35
     корни
    0.35
    啜
    0.35
    순
    0.35
    сс
    0.35
    POSITIVE LOGITS
     among
    0.95
     parmi
    0.91
    Among
    0.91
    among
    0.86
     amongst
    0.85
     Among
    0.82
     dentre
    0.80
     Amongst
    0.77
    śród
    0.76
     중에서
    0.75
    Act Density 0.038%

    No Known Activations