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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     civilization
    -0.07
     cc
    -0.07
     Blood
    -0.07
    pop
    -0.07
     silicon
    -0.07
     vin
    -0.07
    بير
    -0.07
     Pref
    -0.06
     mounting
    -0.06
    amus
    -0.06
    POSITIVE LOGITS
    evenodd
    0.07
    袖
    0.07
     reminders
    0.06
    SignUp
    0.06
     delve
    0.06
    /";↵
    0.06
    _passwd
    0.06
     weiter
    0.06
    /';↵↵
    0.06
    fans
    0.06
    Act Density 0.025%

    No Known Activations