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

    Neuronpedia

    INDEX
    Explanations

    cryptography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sticking
    -0.07
    借鉴
    -0.07
    =""
    -0.07
     earned
    -0.06
    _li
    -0.06
    /general
    -0.06
    意外
    -0.06
    🏸
    -0.06
    _im
    -0.06
    补助
    -0.06
    POSITIVE LOGITS
    atom
    0.08
    hydro
    0.08
     ELF
    0.08
    ᔭ
    0.08
     directors
    0.07
    aryl
    0.07
     реак
    0.07
     выполня
    0.07
    cycle
    0.07
    point
    0.07
    Act Density 0.013%

    No Known Activations