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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Souls
    -0.06
     Fen
    -0.06
     Margaret
    -0.06
     Exped
    -0.06
    Penn
    -0.06
     Wahl
    -0.06
     Tests
    -0.06
    Kind
    -0.05
     Test
    -0.05
     Apost
    -0.05
    POSITIVE LOGITS
     distortion
    0.07
     склад
    0.07
    ้ง
    0.07
     chevy
    0.07
    location
    0.07
    好
    0.07
    locations
    0.06
    Installing
    0.06
    tokenizer
    0.06
    larak
    0.06
    Act Density 0.001%

    No Known Activations