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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Terr
    -0.07
     وفق
    -0.07
     Bean
    -0.06
    ami
    -0.06
     Seen
    -0.06
     Side
    -0.06
    -0.06
     Kale
    -0.06
    -temp
    -0.06
     لك
    -0.06
    POSITIVE LOGITS
     categorical
    0.07
    _axis
    0.06
    urray
    0.06
    $self
    0.06
    '.↵↵
    0.06
    릉
    0.06
     مصر
    0.06
    ство
    0.06
     среди
    0.06
    _attempts
    0.06
    Act Density 0.015%

    No Known Activations