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

    Neuronpedia

    INDEX
    Explanations

    solar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    改革
    -0.08
     breach
    -0.08
    Ele
    -0.08
     متحد
    -0.07
     следующие
    -0.07
    赛
    -0.07
     اتحاد
    -0.07
     borough
    -0.07
    ∀
    -0.07
     territor
    -0.07
    POSITIVE LOGITS
     gens
    0.08
    .ham
    0.08
     erzählen
    0.08
     વ્યવ
    0.08
     survived
    0.08
     survive
    0.07
     stok
    0.07
     ideally
    0.07
     संच
    0.07
     kum
    0.07
    Act Density 0.007%

    No Known Activations