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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     savory
    -0.07
    下的
    -0.06
    感官
    -0.06
    此事
    -0.06
     hoped
    -0.06
     simplified
    -0.06
    омер
    -0.06
     cap
    -0.06
    필
    -0.06
    שטר
    -0.06
    POSITIVE LOGITS
     musica
    0.07
     Borders
    0.07
    อาก
    0.06
    gabe
    0.06
    礼拜
    0.06
    ();
    0.06
    acente
    0.06
    getBlock
    0.06
     NEGLIGENCE
    0.06
    unas
    0.06
    Act Density 0.019%

    No Known Activations