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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =new
    -0.07
    ITU
    -0.07
    ниц
    -0.07
    駅徒歩
    -0.07
    Remarks
    -0.06
    permanent
    -0.06
    +xml
    -0.06
     되었다
    -0.06
     obsolete
    -0.06
    .ApplyResources
    -0.06
    POSITIVE LOGITS
     undercover
    0.07
     відч
    0.06
     Guitar
    0.06
     Shirley
    0.06
     RP
    0.06
     zdraví
    0.06
     Carroll
    0.06
    phere
    0.06
     Shard
    0.06
    usize
    0.06
    Act Density 0.026%

    No Known Activations