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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dol
    0.81
     balloons
    0.63
    lets
    0.63
     Bur
    0.62
    셔서
    0.61
    written
    0.60
     malos
    0.60
    ICLES
    0.60
    চিতে
    0.59
    Bur
    0.59
    POSITIVE LOGITS
     surrounding
    0.75
    Programming
    0.74
     programming
    0.71
     código
    0.71
     hooked
    0.71
     kode
    0.70
    的代码
    0.70
    ABAD
    0.69
    编程
    0.68
     hooking
    0.68
    Act Density 0.002%

    No Known Activations