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

    Neuronpedia

    INDEX
    Explanations

    avir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lust
    -0.07
     defa
    -0.06
    oke
    -0.06
     потен
    -0.06
    .kode
    -0.06
     вал
    -0.06
     vielleicht
    -0.06
     dips
    -0.06
    ileaks
    -0.06
     Emb
    -0.06
    POSITIVE LOGITS
    avir
    0.10
     precipitation
    0.07
    CAN
    0.06
    ै?↵
    0.06
    ้านด
    0.06
    western
    0.06
     VPN
    0.06
    onavir
    0.06
    Composition
    0.06
    사를
    0.06
    Act Density 0.002%

    No Known Activations