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

    Neuronpedia

    INDEX
    Explanations

    prioritize support requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estuary
    0.49
     estuaries
    0.48
    abhavena
    0.47
     সৌরভ
    0.47
     brisket
    0.46
     marsh
    0.46
    Rename
    0.46
     Ê
    0.46
    acchati
    0.46
     ওপর
    0.44
    POSITIVE LOGITS
    日本
    0.60
    本
    0.55
    化
    0.53
     ഹിന്ദു
    0.50
    金
    0.49
    一
    0.48
    ن
    0.47
    三
    0.47
    noz
    0.45
    ل
    0.45
    Act Density 0.008%

    No Known Activations