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

    Neuronpedia

    INDEX
    Explanations

    Switzerland

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AFE
    -0.06
    /Gate
    -0.06
    cohol
    -0.06
     tortured
    -0.06
     veterin
    -0.06
     وأ
    -0.06
     spouses
    -0.06
     �
    -0.06
     condemn
    -0.06
    (ac
    -0.06
    POSITIVE LOGITS
    }";↵
    0.07
     temel
    0.06
     dej
    0.06
    대학교
    0.06
    .getWriter
    0.06
     helfen
    0.06
     instancia
    0.06
    .utility
    0.06
    blocking
    0.06
    central
    0.06
    Act Density 0.075%

    No Known Activations