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

    Neuronpedia

    INDEX
    Explanations

    Angular/Typescript code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    닺
    -0.07
     maintains
    -0.07
    ご利用
    -0.07
     persists
    -0.07
     amor
    -0.07
    ват
    -0.07
    _die
    -0.07
    乸
    -0.07
    ambia
    -0.07
     ambos
    -0.07
    POSITIVE LOGITS
     imperial
    0.07
     преп
    0.07
    树木
    0.07
    EVER
    0.07
     ספרים
    0.07
     LABEL
    0.07
    零部件
    0.07
     Interpreter
    0.07
     carcin
    0.07
    疖
    0.07
    Act Density 0.005%

    No Known Activations