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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Github
    -0.07
     Capture
    -0.07
    _GPS
    -0.06
    計劃
    -0.06
     Instagram
    -0.06
    yard
    -0.06
    ']=
    -0.06
    рем
    -0.06
    istem
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     कन
    0.07
    _resume
    0.07
     distributes
    0.07
     sodom
    0.06
     (*)
    0.06
     thrill
    0.06
     kurz
    0.06
     생활
    0.06
     bikini
    0.06
    ौं
    0.06
    Act Density 0.029%

    No Known Activations