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

    Neuronpedia

    INDEX
    Explanations

    left behind or alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mant
    0.25
    FAILED
    0.24
    olik
    0.24
    ávez
    0.23
    ␊
    0.23
    ции
    0.23
     manten
    0.23
    ઞ
    0.23
     nigra
    0.23
     Архиви
    0.22
    POSITIVE LOGITS
     behind
    0.54
     untouched
    0.50
     atrás
    0.46
    behind
    0.43
     unattended
    0.43
     unanswered
    0.42
     Behind
    0.40
     unchanged
    0.40
     unscathed
    0.40
     alone
    0.38
    Act Density 0.013%

    No Known Activations