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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (strtolower
    -0.07
    BIN
    -0.07
    枧
    -0.06
    атур
    -0.06
    不应
    -0.06
     Words
    -0.06
    娄
    -0.06
    TimeZone
    -0.06
    env
    -0.06
    /opt
    -0.06
    POSITIVE LOGITS
    שיחה
    0.07
    으며
    0.07
    ança
    0.07
    ;;
    0.07
    妹妹
    0.07
    ($('.
    0.06
    sortable
    0.06
     Psycho
    0.06
    时隔
    0.06
     Garlic
    0.06
    Act Density 0.016%

    No Known Activations