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

    Neuronpedia

    INDEX
    Explanations

    VPN and privacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultural
    -0.09
    -↵↵
    -0.08
    .Groups
    -0.08
    manufact
    -0.08
    ilà
    -0.08
    yg
    -0.08
     Secretariat
    -0.08
    anfaat
    -0.08
    िएको
    -0.08
    .products
    -0.07
    POSITIVE LOGITS
     estimation
    0.08
     Tracking
    0.08
     tekem
    0.08
     ISR
    0.08
     refusing
    0.08
     terceros
    0.08
     terceiros
    0.07
     eqq
    0.07
    踪
    0.07
     piste
    0.07
    Act Density 0.007%

    No Known Activations