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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tools
    -0.07
     Tong
    -0.07
    อนด
    -0.07
    ilded
    -0.07
    .MESSAGE
    -0.06
     snakes
    -0.06
     Santos
    -0.06
     Manson
    -0.06
     giao
    -0.06
    assel
    -0.06
    POSITIVE LOGITS
     нев
    0.07
     exig
    0.06
     کوتاه
    0.06
     Canadiens
    0.06
     juven
    0.06
     errores
    0.06
     AU
    0.06
    -plus
    0.06
     허
    0.06
     Thousands
    0.05
    Act Density 0.043%

    No Known Activations