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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     движ
    -0.07
     MQTT
    -0.06
     урож
    -0.06
    -danger
    -0.06
    립
    -0.06
     Rome
    -0.06
     �
    -0.06
     відбувається
    -0.06
    разд
    -0.06
    敢
    -0.06
    POSITIVE LOGITS
    زن
    0.07
     prosec
    0.06
    ompson
    0.06
    atinum
    0.06
    laughs
    0.06
     U
    0.06
     staffers
    0.06
    ApiKey
    0.06
    .stdout
    0.06
     Joseph
    0.06
    Act Density 0.056%

    No Known Activations