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

    Neuronpedia

    INDEX
    Explanations

    refrain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dolar
    -0.07
    δει
    -0.07
    Sector
    -0.07
     капіт
    -0.06
     quot
    -0.06
     Klopp
    -0.06
    Dirty
    -0.06
     bigger
    -0.06
     salsa
    -0.06
     komt
    -0.06
    POSITIVE LOGITS
     Login
    0.07
    threads
    0.07
    واع
    0.07
     vain
    0.07
     EINVAL
    0.07
     Veterans
    0.07
     detain
    0.06
    ################################################################################↵
    0.06
     restarting
    0.06
     budete
    0.06
    Act Density 0.005%

    No Known Activations