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

    Neuronpedia

    INDEX
    Explanations

    this or particular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HANDLE
    -0.07
     secure
    -0.07
     السم
    -0.07
     публі
    -0.07
     لل
    -0.07
    icted
    -0.06
     definition
    -0.06
     Quentin
    -0.06
    IMPORTANT
    -0.06
    _none
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    .ml
    0.07
    .backends
    0.06
     Jord
    0.06
     dönem
    0.06
    >\<
    0.06
    Mahon
    0.05
    ieee
    0.05
     hộ
    0.05
    auth
    0.05
    Act Density 0.024%

    No Known Activations