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

    Neuronpedia

    INDEX
    Explanations

    Transportation and related technical context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^\
    -0.07
     increasing
    -0.07
     importance
    -0.07
    惜
    -0.07
    medi
    -0.06
     acceso
    -0.06
    iran
    -0.06
    uish
    -0.06
    物种
    -0.06
    ierrez
    -0.06
    POSITIVE LOGITS
    Declared
    0.07
    直言
    0.07
    pcb
    0.07
    ALAR
    0.06
     xls
    0.06
    Xd
    0.06
    _stub
    0.06
    RITE
    0.06
     Casting
    0.06
    .hide
    0.06
    Act Density 0.048%

    No Known Activations