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

    Neuronpedia

    INDEX
    Explanations

    behavior change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vě
    -0.06
    vented
    -0.06
    .tab
    -0.06
    '{
    -0.06
    dere
    -0.05
    .
↵
    -0.05
     tématu
    -0.05
     Pointer
    -0.05
     Ether
    -0.05
    _route
    -0.05
    POSITIVE LOGITS
     apart
    0.06
     Düz
    0.06
    وب
    0.06
     Gardens
    0.06
     licking
    0.06
    .Bunifu
    0.06
     велик
    0.06
     ind
    0.06
    �
    0.06
     Bron
    0.06
    Act Density 0.077%

    No Known Activations