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

    Neuronpedia

    INDEX
    Explanations

    task and subtasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ramos
    0.68
    冢
    0.67
     Attendees
    0.66
     denominator
    0.65
     Dealers
    0.65
     Bundes
    0.63
     Correspondent
    0.63
     preempt
    0.62
     ACL
    0.62
     Journalist
    0.62
    POSITIVE LOGITS
    сюда
    0.82
    OUR
    0.80
     चलाया
    0.80
     устро
    0.79
    Snackbar
    0.75
    DH
    0.74
     불구
    0.74
     Plow
    0.72
    सरा
    0.72
    inely
    0.71
    Act Density 0.000%

    No Known Activations