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

    Neuronpedia

    INDEX
    Explanations

    eigen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Moody
    -0.07
    -place
    -0.07
     Horde
    -0.07
    การพ
    -0.07
     vra
    -0.07
    
    -0.06
    _callbacks
    -0.06
    Сп
    -0.06
    لية
    -0.06
     RECORD
    -0.06
    POSITIVE LOGITS
     eigen
    0.15
    Eigen
    0.12
     Eigen
    0.11
     eig
    0.09
    _In
    0.07
    ogen
    0.06
    aign
    0.06
     Nottingham
    0.06
    ien
    0.06
     wasn
    0.06
    Act Density 0.001%

    No Known Activations