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

    Neuronpedia

    INDEX
    Explanations

    instructions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discharge
    0.43
     among
    0.42
     göst
    0.42
     succinctly
    0.41
     دکھ
    0.41
     nieco
    0.40
     mouvements
    0.40
     chest
    0.40
     globe
    0.40
     send
    0.39
    POSITIVE LOGITS
    يل
    0.52
    AZ
    0.45
    Casc
    0.43
    Activate
    0.42
    ல்களை
    0.41
    atus
    0.40
     पती
    0.40
    Resource
    0.39
    BrI
    0.39
    IF
    0.39
    Act Density 9.691%

    No Known Activations