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

    Neuronpedia

    INDEX
    Explanations

    ir

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ped
    -0.07
     üy
    -0.06
     kole
    -0.06
     OTA
    -0.06
     komple
    -0.06
     nama
    -0.06
     exploitation
    -0.06
    yna
    -0.06
    _ordered
    -0.06
    covery
    -0.06
    POSITIVE LOGITS
    Queue
    0.07
     Drain
    0.07
    歴
    0.07
     BER
    0.07
    /TR
    0.06
    工作
    0.06
    ψει
    0.06
    Під
    0.06
     Boundary
    0.06
    mesh
    0.06
    Act Density 0.000%

    No Known Activations