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

    Neuronpedia

    INDEX
    Explanations

    Standing up for beliefs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dens
    -0.06
     perder
    -0.06
     dét
    -0.06
     wavelengths
    -0.06
     cooler
    -0.06
     Dry
    -0.06
     wavelength
    -0.05
    /j
    -0.05
    。',↵
    -0.05
     condu
    -0.05
    POSITIVE LOGITS
     "("
    0.08
    に関
    0.07
    (keyword
    0.07
     وم
    0.07
     videot
    0.07
    IpAddress
    0.07
     بالاتر
    0.07
    ":"+
    0.07
     Tam
    0.07
    сок
    0.07
    Act Density 0.021%

    No Known Activations