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

    Neuronpedia

    INDEX
    Explanations

    mythology and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifestyles
    -0.08
     tha
    -0.08
     reckon
    -0.08
     egentligen
    -0.08
    ിരിക്ക
    -0.08
     Collect
    -0.07
     pressures
    -0.07
    تو
    -0.07
     Nitro
    -0.07
     zahl
    -0.07
    POSITIVE LOGITS
    (sim
    0.08
     maternal
    0.08
    [source
    0.08
    Mater
    0.08
    mater
    0.07
    authorized
    0.07
    /random
    0.07
    idf
    0.07
    /id
    0.07
     importa
    0.07
    Act Density 0.023%

    No Known Activations