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

    Neuronpedia

    INDEX
    Explanations

    code, configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    aight
    -0.07
     predecessors
    -0.07
    רגש
    -0.07
    ']])↵
    -0.06
    🔞
    -0.06
    }}},↵
    -0.06
    .........
    -0.06
    خطوط
    -0.06
    .rmtree
    -0.06
    POSITIVE LOGITS
     harvested
    0.07
     Post
    0.07
     bom
    0.07
     Univers
    0.07
     privat
    0.07
    	center
    0.07
    ι
    0.07
    Hi
    0.07
    ersed
    0.07
    .Authorization
    0.07
    Act Density 0.003%

    No Known Activations