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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    っ�
    -0.07
    ﾄ
    -0.07
    bx
    -0.07
    executor
    -0.06
    (para
    -0.06
    annotation
    -0.06
    	cf
    -0.06
    ському
    -0.06
     Sacred
    -0.06
    pegawai
    -0.06
    POSITIVE LOGITS
    icles
    0.06
    /)
    0.06
     dental
    0.06
     substitute
    0.06
     interrupted
    0.06
     THE
    0.06
     آغاز
    0.06
    _REV
    0.06
     disjoint
    0.06
     cane
    0.06
    Act Density 0.038%

    No Known Activations