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

    Neuronpedia

    INDEX
    Explanations

    improve/reduce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Floating
    -0.08
    COMPARE
    -0.06
    aju
    -0.06
    heap
    -0.06
    _opcode
    -0.06
    .shutdown
    -0.06
    Merchant
    -0.06
    _rule
    -0.06
     rõ
    -0.06
    .apps
    -0.06
    POSITIVE LOGITS
    mast
    0.07
    包括
    0.06
    kiem
    0.06
     responding
    0.06
     plumbing
    0.06
     cared
    0.06
     reporting
    0.06
     applying
    0.06
    .Di
    0.06
    (big
    0.06
    Act Density 0.049%

    No Known Activations