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

    Neuronpedia

    INDEX
    Explanations

    measuring time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bannon
    -0.06
     subt
    -0.06
     bcm
    -0.06
    ซ
    -0.06
     ště
    -0.05
    ﾄ
    -0.05
     recipients
    -0.05
    客户
    -0.05
    られる
    -0.05
    这些
    -0.05
    POSITIVE LOGITS
    [],
    0.06
    Spell
    0.06
    /user
    0.06
    omen
    0.06
    ocommerce
    0.06
    га
    0.06
     frau
    0.06
    .default
    0.06
     confuse
    0.06
    ewitness
    0.06
    Act Density 0.034%

    No Known Activations