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

    Neuronpedia

    INDEX
    Explanations

    breathing and oxygen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.67
     écrite
    -0.59
    RegistryLite
    -0.58
    endphp
    -0.58
    WriteTagHelper
    -0.57
     attacc
    -0.56
     يتيمه
    -0.56
     invokingState
    -0.53
     &___
    -0.53
     dichiarato
    -0.53
    POSITIVE LOGITS
     positive
    0.51
     insuff
    0.48
    positive
    0.47
     ventilation
    0.47
    app
    0.47
     encor
    0.46
    posti
    0.45
     mano
    0.44
    Positive
    0.44
    țional
    0.42
    Act Density 0.002%

    No Known Activations