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

    Neuronpedia

    INDEX
    Explanations

    Jira issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Natalie
    -0.08
     בקל
    -0.07
    懊
    -0.07
     đu
    -0.07
    ckt
    -0.06
     MEM
    -0.06
     IEEE
    -0.06
     annunci
    -0.06
     Indoor
    -0.06
     Sche
    -0.06
    POSITIVE LOGITS
     yourselves
    0.07
    إصابة
    0.07
    asbourg
    0.07
    ?s
    0.07
    困扰
    0.07
    岠
    0.07
    lights
    0.07
    ę
    0.07
    类型
    0.07
    icking
    0.07
    Act Density 0.000%

    No Known Activations