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

    Neuronpedia

    INDEX
    Explanations

    cid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supremacist
    -0.07
     dictated
    -0.06
     totaling
    -0.06
    (Table
    -0.06
     whatsapp
    -0.06
    ＿__
    -0.06
     Hardy
    -0.06
     líder
    -0.06
    Kal
    -0.06
     Método
    -0.05
    POSITIVE LOGITS
    える
    0.07
    کم
    0.07
     він
    0.07
    kov
    0.06
    ського
    0.06
    ervice
    0.06
    лова
    0.06
    ському
    0.06
    ��
    0.06
     Brom
    0.06
    Act Density 0.000%

    No Known Activations