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

    Neuronpedia

    INDEX
    Explanations

    Scripps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ket
    -0.08
    (Self
    -0.07
    现实
    -0.07
     kị
    -0.07
     deter
    -0.07
     Vaccine
    -0.07
    hế
    -0.07
    차
    -0.07
    Tek
    -0.07
    훈
    -0.07
    POSITIVE LOGITS
    ewriter
    0.08
     Entrance
    0.08
    Increment
    0.08
    appendChild
    0.07
     obligation
    0.07
    _source
    0.07
     patch
    0.07
     untouched
    0.07
    ・・・↵↵
    0.07
    .Task
    0.07
    Act Density 0.005%

    No Known Activations