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

    Neuronpedia

    INDEX
    Explanations

    Geographical locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Helper
    -0.07
    .connector
    -0.06
    kladní
    -0.06
    覺
    -0.06
    ========↵
    -0.06
    Credit
    -0.06
    '.↵↵
    -0.06
     سفر
    -0.06
    нику
    -0.06
    	stat
    -0.06
    POSITIVE LOGITS
    งก
    0.07
    oref
    0.06
    arch
    0.06
    )<=
    0.06
     lia
    0.06
    allas
    0.06
     hashed
    0.06
     PI
    0.06
    (xx
    0.06
     pun
    0.05
    Act Density 0.040%

    No Known Activations