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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Driving
    -0.07
     Venezuela
    -0.07
     Desire
    -0.07
     всего
    -0.07
     Gross
    -0.07
     хоч
    -0.07
     Paris
    -0.07
     reserve
    -0.07
    .android
    -0.06
    `.↵↵
    -0.06
    POSITIVE LOGITS
    ڪ
    0.07
    iptables
    0.07
    bv
    0.07
    ’S
    0.06
    uala
    0.06
    �
    0.06
     LGBTQ
    0.06
     <↵
    0.06
     начал
    0.06
    SERVER
    0.06
    Act Density 0.110%

    No Known Activations