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

    Neuronpedia

    INDEX
    Explanations

    verdict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gleich
    -0.07
    roperty
    -0.07
     Hollow
    -0.06
    institution
    -0.06
     �
    -0.06
     oste
    -0.06
     washer
    -0.06
     borrow
    -0.06
     ль
    -0.06
     충
    -0.06
    POSITIVE LOGITS
     verdict
    0.08
     /^
    0.07
    �
    0.07
    Perfil
    0.07
    üyoruz
    0.07
    Verifier
    0.07
    ὶ
    0.07
    ¯¯
    0.07
     :/:
    0.07
    Results
    0.06
    Act Density 0.001%

    No Known Activations