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

    Neuronpedia

    INDEX
    Explanations

    changing quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hôn
    -0.07
     Helena
    -0.07
    vang
    -0.07
    _timeout
    -0.06
    ά
    -0.06
    vec
    -0.06
     hills
    -0.06
     Victims
    -0.06
    ुच
    -0.06
     waiver
    -0.06
    POSITIVE LOGITS
    inkle
    0.06
    .uni
    0.06
    __.'/
    0.06
     insisted
    0.06
     từng
    0.06
    оу
    0.06
     personalize
    0.06
     BCM
    0.06
     mgr
    0.05
    �ん
    0.05
    Act Density 0.110%

    No Known Activations