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

    Neuronpedia

    INDEX
    Explanations

    Bear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enclosed
    -0.07
    _reg
    -0.07
    くん
    -0.06
     Raiders
    -0.06
    の
    -0.06
     downward
    -0.06
    坦
    -0.06
    或者
    -0.06
    医
    -0.06
     "^
    -0.06
    POSITIVE LOGITS
    .IMAGE
    0.07
    .art
    0.07
    udded
    0.06
    opolitan
    0.06
    aviours
    0.06
     Twist
    0.06
    �
    0.06
    manı
    0.06
    .background
    0.06
    eldorf
    0.06
    Act Density 0.002%

    No Known Activations