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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    되어
    -0.08
     책
    -0.07
     shirt
    -0.06
     dramas
    -0.06
    ρούν
    -0.06
    class
    -0.06
    	no
    -0.06
     medicines
    -0.06
    .""
    -0.06
     Framework
    -0.06
    POSITIVE LOGITS
    _STR
    0.06
    _GT
    0.06
     AUT
    0.06
    enties
    0.06
     FirebaseDatabase
    0.06
    eresa
    0.06
    queeze
    0.06
     Istanbul
    0.06
    行
    0.06
    [__
    0.06
    Act Density 0.002%

    No Known Activations