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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    `.`
    -0.07
    ',[
    -0.07
     ;)↵↵
    -0.06
     steril
    -0.06
    周收录
    -0.06
     درجه
    -0.06
     ruin
    -0.06
    gebra
    -0.06
     СП
    -0.06
     dup
    -0.06
    POSITIVE LOGITS
    Christopher
    0.07
    Exceptions
    0.07
    acula
    0.06
    蛛
    0.06
     hotelu
    0.06
    Email
    0.06
    _lengths
    0.06
    (rr
    0.06
     printk
    0.06
     boton
    0.06
    Act Density 0.018%

    No Known Activations