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

    Neuronpedia

    INDEX
    Explanations

    mm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cloak
    -0.07
    _cpus
    -0.07
     Pierre
    -0.06
    .age
    -0.06
    SGlobal
    -0.06
    slt
    -0.06
     XOR
    -0.06
     Coaching
    -0.06
     Zhou
    -0.06
    EQUAL
    -0.06
    POSITIVE LOGITS
     instr
    0.08
    虽
    0.06
     LEN
    0.06
     Haram
    0.06
     carnival
    0.06
     astr
    0.06
     Programm
    0.06
    ，要
    0.06
     DIY
    0.06
    utenberg
    0.06
    Act Density 0.001%

    No Known Activations