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

    Neuronpedia

    INDEX
    Explanations

    often

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    完
    -0.06
    _ACT
    -0.06
    yd
    -0.06
    vised
    -0.06
     convincing
    -0.06
    _RESET
    -0.06
    .hex
    -0.06
    出版
    -0.06
    .st
    -0.06
     pumping
    -0.06
    POSITIVE LOGITS
     Often
    0.07
     Argentina
    0.07
     positively
    0.06
    ，可
    0.06
     brill
    0.06
     INCLUDING
    0.06
     Still
    0.06
    ItemCount
    0.06
     solidarity
    0.06
     dispersion
    0.06
    Act Density 0.066%

    No Known Activations