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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تت
    -0.07
    %(
    -0.07
    修改
    -0.07
     Grove
    -0.06
    OPTARG
    -0.06
    は
    -0.06
    _pd
    -0.06
    (stop
    -0.06
     podium
    -0.06
    _it
    -0.06
    POSITIVE LOGITS
     esc
    0.07
     アル
    0.06
    \"");↵
    0.06
    imeType
    0.06
    lox
    0.06
    .');↵
    0.06
    offline
    0.06
    ”.↵
    0.06
    )"↵
    0.06
    оза
    0.06
    Act Density 0.005%

    No Known Activations