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

    Neuronpedia

    INDEX
    Explanations

    distribution restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doing
    -0.07
     voiture
    -0.07
    Crime
    -0.07
    _q
    -0.06
     Dems
    -0.06
     prvním
    -0.06
    �i
    -0.06
     times
    -0.06
    енно
    -0.06
     Poetry
    -0.06
    POSITIVE LOGITS
    (handles
    0.07
    aryawan
    0.06
     sed
    0.06
    _principal
    0.06
    getSingleton
    0.06
    ısında
    0.06
    /vnd
    0.06
     กร
    0.06
     ใช
    0.06
    afs
    0.06
    Act Density 0.004%

    No Known Activations