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

    Neuronpedia

    INDEX
    Explanations

    hydr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    label
    -0.07
     election
    -0.06
    .fake
    -0.06
     circles
    -0.06
    KIT
    -0.06
     cipher
    -0.06
    acos
    -0.06
    ()<<
    -0.06
     curse
    -0.06
     audio
    -0.06
    POSITIVE LOGITS
     pinterest
    0.08
    bohydr
    0.08
     hecho
    0.07
     jen
    0.07
     jsonify
    0.06
        ↵    ↵    ↵    ↵
    0.06
    uta
    0.06
    hay
    0.06
     Hlav
    0.06
    .LayoutInflater
    0.06
    Act Density 0.002%

    No Known Activations