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

    Neuronpedia

    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Won
    -0.08
     thì
    -0.08
    �
    -0.07
    lığı
    -0.06
    .rect
    -0.06
    uC
    -0.06
    owntown
    -0.06
     kök
    -0.06
    udio
    -0.06
     rozsah
    -0.06
    POSITIVE LOGITS
     Ні
    0.07
    levision
    0.07
     Debbie
    0.06
    hospital
    0.06
     getpid
    0.06
    nelly
    0.06
    レビ
    0.06
     BLE
    0.06
     Hd
    0.06
    ”。
    0.06
    Act Density 0.008%

    No Known Activations