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

    Neuronpedia

    INDEX
    Explanations

    counting down numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    re
    0.78
    ts
    0.77
    to
    0.75
     Questionnaire
    0.74
    ini
    0.71
     것이다
    0.71
    Farm
    0.70
     Social
    0.69
     and
    0.68
     Fund
    0.68
    POSITIVE LOGITS
     dimers
    0.89
     beets
    0.81
    லூர்
    0.80
    кість
    0.78
     ISPs
    0.78
     RIS
    0.77
    кої
    0.77
     chlorides
    0.77
    ennem
    0.76
     lackluster
    0.76
    Act Density 0.001%

    No Known Activations