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

    Neuronpedia

    INDEX
    Explanations

    i or Shi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ketøy
    -0.06
    roveň
    -0.06
     gerekli
    -0.06
    ука
    -0.06
    Drawing
    -0.06
     builders
    -0.06
    interaction
    -0.06
    uur
    -0.06
    Chat
    -0.06
    ’↵↵
    -0.06
    POSITIVE LOGITS
    shot
    0.07
    rie
    0.07
    ovně
    0.07
    igua
    0.07
     �
    0.07
    reur
    0.06
    icorn
    0.06
     期
    0.06
    lias
    0.06
    urved
    0.06
    Act Density 0.005%

    No Known Activations