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

    Neuronpedia

    INDEX
    Explanations

    diverse backgrounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     якая
    0.50
     zagro
    0.49
     وق
    0.49
     delivering
    0.46
     Vali
    0.46
    constraint
    0.46
    introducing
    0.46
     благо
    0.46
    limiting
    0.45
     כאשר
    0.45
    POSITIVE LOGITS
    ystore
    0.46
     EMPLOY
    0.46
    冰
    0.44
     cafe
    0.43
    рино
    0.41
     /></
    0.41
    PNG
    0.41
    DCs
    0.41
    ografico
    0.40
    AC
    0.40
    Act Density 0.000%

    No Known Activations