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

    Neuronpedia

    INDEX
    Explanations

    battles and attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ras
    -0.07
    ificados
    -0.07
    ustralia
    -0.06
    kh
    -0.06
     Vườn
    -0.06
    .FirebaseAuth
    -0.06
    圖
    -0.06
    าคม
    -0.06
    ?a
    -0.06
    п
    -0.06
    POSITIVE LOGITS
     outlaw
    0.07
    categories
    0.06
     короб
    0.06
     DNS
    0.06
    ={↵
    0.06
    elix
    0.06
     распростран
    0.06
     dispens
    0.06
     Cold
    0.06
     �
    0.06
    Act Density 0.025%

    No Known Activations