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

    Neuronpedia

    INDEX
    Explanations

    mysteries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hews
    -0.08
     pà
    -0.08
     tiek
    -0.08
     килом
    -0.08
     forgiven
    -0.07
    ouli
    -0.07
     så
    -0.07
     discussion
    -0.07
    adau
    -0.07
     конеч
    -0.07
    POSITIVE LOGITS
     myster
    0.11
     mystérie
    0.10
     mysterious
    0.09
     malfunction
    0.09
    Myst
    0.09
     রহ
    0.09
     recently
    0.08
     inexp
    0.08
     unusually
    0.08
     Wilder
    0.08
    Act Density 0.029%

    No Known Activations