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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    suite
    -0.07
     Luật
    -0.07
    分明
    -0.07
     plata
    -0.07
    _Data
    -0.07
    comments
    -0.07
    持续推进
    -0.07
     不
    -0.07
     Putin
    -0.07
    icious
    -0.07
    POSITIVE LOGITS
    ']>;↵
    0.08
    .questions
    0.07
    (filters
    0.07
    .fs
    0.07
     XYZ
    0.06
    	server
    0.06
    udy
    0.06
    eref
    0.06
    IONS
    0.06
    allax
    0.06
    Act Density 0.053%

    No Known Activations