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

    Neuronpedia

    INDEX
    Explanations

    intensity markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    偵
    -0.07
    _floor
    -0.07
    InSection
    -0.07
     suddenly
    -0.07
    فى
    -0.07
    吟
    -0.07
    ,idx
    -0.07
    狂
    -0.06
    dź
    -0.06
    (indexPath
    -0.06
    POSITIVE LOGITS
    Usage
    0.08
     chatte
    0.07
     userService
    0.07
    משכ
    0.07
    共和
    0.07
     pens
    0.07
    用户
    0.07
     جانب
    0.07
    (('
    0.07
    Charsets
    0.07
    Act Density 0.238%

    No Known Activations