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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BIT
    -0.07
     ×
    -0.07
    -entry
    -0.07
    spin
    -0.07
    专项资金
    -0.07
    .logger
    -0.06
     минут
    -0.06
    后排
    -0.06
    一间
    -0.06
     Sid
    -0.06
    POSITIVE LOGITS
    .ignore
    0.09
     котор
    0.09
    啸
    0.08
    wild
    0.07
     literary
    0.07
     crawling
    0.07
    崖
    0.07
    קט
    0.07
    efe
    0.07
    ke
    0.07
    Act Density 0.078%

    No Known Activations