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

    Neuronpedia

    INDEX
    Explanations

    how's it going asking status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distr
    0.66
     remotely
    0.62
    Phone
    0.62
     spans
    0.62
     পারিল
    0.62
     Phone
    0.60
     BIT
    0.59
     callbacks
    0.58
     Adm
    0.58
    ilipp
    0.58
    POSITIVE LOGITS
     goes
    0.78
     going
    0.73
     go
    0.70
    go
    0.68
    gå
    0.66
    apus
    0.65
     allez
    0.61
     pergi
    0.61
    あす楽
    0.59
    த்திற்கு
    0.59
    Act Density 0.099%

    No Known Activations