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

    Neuronpedia

    INDEX
    Explanations

    HTML entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haystack
    -0.27
    igu
    -0.27
    ellungen
    -0.27
     dumps
    -0.27
    pty
    -0.27
    iguous
    -0.26
    æĬ¼
    -0.26
    ataires
    -0.26
    Inspectable
    -0.25
    çIJĨæĥ³ä¿¡å¿µ
    -0.25
    POSITIVE LOGITS
    mage
    0.26
    mid
    0.26
    ite
    0.25
    инÑĦ
    0.24
    timeofday
    0.24
    esis
    0.24
    åįļçī©
    0.24
    {-
    0.24
    ITE
    0.24
    Ãło
    0.24
    Act Density 0.158%

    No Known Activations