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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    께
    -0.07
    迫
    -0.07
    ีด
    -0.07
    шив
    -0.06
     чуд
    -0.06
    �
    -0.06
    ophage
    -0.06
     зуст
    -0.06
    akest
    -0.06
    xCF
    -0.06
    POSITIVE LOGITS
    Người
    0.07
    oto
    0.07
     veterinarian
    0.06
     tunnels
    0.06
    _Left
    0.06
     resett
    0.06
     Kabul
    0.06
    Kind
    0.06
    Power
    0.06
     influencers
    0.06
    Act Density 0.000%

    No Known Activations