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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onchange
    -0.08
    Transition
    -0.07
    Pipeline
    -0.07
    热情
    -0.06
     grids
    -0.06
     REP
    -0.06
     onCreate
    -0.06
    NOP
    -0.06
    资本
    -0.06
     mov
    -0.06
    POSITIVE LOGITS
    枸杞
    0.08
    .finish
    0.07
    .amazon
    0.07
     canned
    0.07
    (bc
    0.07
    .book
    0.07
    (Controller
    0.07
    _VARIABLE
    0.07
    奄
    0.07
    /perl
    0.07
    Act Density 0.003%

    No Known Activations