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

    Neuronpedia

    INDEX
    Explanations

    those these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovaných
    -0.07
     �
    -0.07
    xde
    -0.07
     اینکه
    -0.06
     antis
    -0.06
    (m
    -0.06
    음
    -0.06
     нічого
    -0.06
    etí
    -0.06
    yg
    -0.06
    POSITIVE LOGITS
     hành
    0.07
     Poker
    0.07
    VM
    0.07
    .glob
    0.06
    งใน
    0.06
    35
    0.06
     Bosch
    0.06
    قيق
    0.06
    REF
    0.06
     stating
    0.06
    Act Density 0.096%

    No Known Activations