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

    Neuronpedia

    INDEX
    Explanations

    small parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    authentication
    -0.07
     denotes
    -0.07
     regular
    -0.07
     reorgan
    -0.07
    administr
    -0.07
    ldt
    -0.07
     administration
    -0.07
    -war
    -0.07
     протест
    -0.07
    war
    -0.07
    POSITIVE LOGITS
     sigurn
    0.08
    averse
    0.08
    ENTO
    0.08
     benda
    0.08
     //"
    0.08
     //----------------
    0.08
     Accident
    0.08
     �
    0.08
    เด็ก
    0.08
     Resolve
    0.08
    Act Density 0.022%

    No Known Activations