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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enet
    -0.07
     wreck
    -0.07
     climate
    -0.07
     Western
    -0.07
     Polly
    -0.07
    Eastern
    -0.06
    Federal
    -0.06
     прив
    -0.06
    forth
    -0.06
    Mir
    -0.06
    POSITIVE LOGITS
    있는
    0.06
     socket
    0.06
    queryParams
    0.06
    М
    0.06
     م
    0.06
    estival
    0.06
     ode
    0.05
     Flor
    0.05
    发生
    0.05
    blings
    0.05
    Act Density 0.098%

    No Known Activations