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

    Neuronpedia

    INDEX
    Explanations

    Science and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vend
    -0.07
    	headers
    -0.06
     gener
    -0.06
     Horn
    -0.06
     policym
    -0.06
    :↵↵
    -0.06
    Ids
    -0.06
     below
    -0.06
     Att
    -0.06
     (*)(
    -0.06
    POSITIVE LOGITS
    pective
    0.08
    ANDING
    0.07
     subtract
    0.07
     despre
    0.06
    shutdown
    0.06
    chein
    0.06
    нула
    0.06
     شخصی
    0.06
    iliated
    0.06
     เกม
    0.06
    Act Density 0.104%

    No Known Activations