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

    Neuronpedia

    INDEX
    Explanations

    allow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ();↵↵↵
    -0.07
     electro
    -0.06
    erchant
    -0.06
    126
    -0.06
     Над
    -0.06
     messages
    -0.06
     Themes
    -0.06
    _dic
    -0.06
     Backup
    -0.06
     cat
    -0.06
    POSITIVE LOGITS
     allowing
    0.09
     allow
    0.09
     izin
    0.07
    oran
    0.07
     lessen
    0.07
    som
    0.07
     allowed
    0.07
    Allows
    0.07
    alus
    0.07
    滑
    0.07
    Act Density 0.033%

    No Known Activations