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

    Neuronpedia

    INDEX
    Explanations

    half-life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XM
    -0.06
    应
    -0.06
     เว
    -0.06
     intentions
    -0.06
     horny
    -0.06
    Todo
    -0.06
    �
    -0.06
     नह
    -0.06
    Professional
    -0.06
     مرب
    -0.06
    POSITIVE LOGITS
     }*/↵↵
    0.07
     noveller
    0.06
    /Card
    0.06
     oci
    0.06
     mobile
    0.06
    `"]↵
    0.06
     λο
    0.06
     Allocate
    0.06
    []{↵
    0.06
     contract
    0.06
    Act Density 0.018%

    No Known Activations