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

    Neuronpedia

    INDEX
    Explanations

    Etymology of words, names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oward
    -0.27
    ill
    -0.26
    áºŃu
    -0.26
     priv
    -0.25
    imeo
    -0.25
     Foley
    -0.24
    类似
    -0.24
    á»ĭnh
    -0.24
    硬
    -0.24
    ines
    -0.24
    POSITIVE LOGITS
     central
    0.29
    æijĬ
    0.26
     batch
    0.26
    ÑĤаÑĢ
    0.26
    âĬĸ
    0.26
    梢
    0.25
     sweeping
    0.25
    (batch
    0.25
     sweeps
    0.24
     mascara
    0.24
    Act Density 0.002%

    No Known Activations