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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .activ
    -0.07
    -pad
    -0.06
    นด
    -0.06
     жінок
    -0.06
    CN
    -0.06
     жін
    -0.06
    Pause
    -0.06
     empty
    -0.06
    舍
    -0.06
    queda
    -0.06
    POSITIVE LOGITS
     join
    0.06
     reinforced
    0.06
     Markets
    0.06
    ondrous
    0.06
    ardless
    0.06
     thermo
    0.06
     daring
    0.06
    inations
    0.06
     Unlike
    0.06
     onCancel
    0.06
    Act Density 0.014%

    No Known Activations