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

    Neuronpedia

    INDEX
    Explanations

    expansive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    er
    -0.68
     Tree
    -0.52
    iya
    -0.52
    erent
    -0.52
    ه
    -0.50
    Vrij
    -0.48
    eh
    -0.48
     din
    -0.47
    resizingMask
    -0.47
    ips
    -0.47
    POSITIVE LOGITS
     Diſ
    0.59
     touristes
    0.59
     Majefty
    0.59
    +#+#
    0.58
    رشف
    0.56
     Shakspeare
    0.56
     LUMP
    0.56
     sélectionnés
    0.55
     Thebes
    0.55
     suon
    0.55
    Act Density 0.488%

    No Known Activations