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

    Neuronpedia

    INDEX
    Explanations

    Reality and expectations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Target
    -0.07
     recommendation
    -0.07
     derechos
    -0.07
    lid
    -0.07
    attice
    -0.07
     Gallery
    -0.06
    (action
    -0.06
     tremend
    -0.06
     painters
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     представляет
    0.07
     Haziran
    0.07
    олот
    0.07
    ><?=
    0.06
    粗
    0.06
    ј
    0.06
    ۴۰
    0.06
    toContain
    0.06
    ktion
    0.06
     Şubat
    0.06
    Act Density 0.161%

    No Known Activations