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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clarification
    -0.07
     durable
    -0.06
    rtype
    -0.06
    /message
    -0.06
    聘
    -0.06
    يرة
    -0.06
     rer
    -0.06
     correlations
    -0.06
    credit
    -0.06
    าคาร
    -0.06
    POSITIVE LOGITS
     porte
    0.06
     إل
    0.06
     prend
    0.06
    煙
    0.06
     ili
    0.06
     жид
    0.06
    콜
    0.06
     сви
    0.06
    ・マ
    0.06
    Subjects
    0.06
    Act Density 0.001%

    No Known Activations