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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    슈
    -0.07
     včetně
    -0.06
     Sor
    -0.06
     abusive
    -0.06
    黒
    -0.06
     ingenious
    -0.06
     Fak
    -0.06
     lawsuits
    -0.06
    북도
    -0.05
    043
    -0.05
    POSITIVE LOGITS
     streamlined
    0.15
     streamline
    0.13
    efeller
    0.07
     ألمان
    0.07
    Fixed
    0.07
    oggled
    0.07
    BMW
    0.07
     INA
    0.06
     personn
    0.06
    لاین
    0.06
    Act Density 0.002%

    No Known Activations