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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оке
    -0.08
     erle
    -0.07
     lé
    -0.07
     venom
    -0.06
     ModelRenderer
    -0.06
     espos
    -0.06
     Ren
    -0.06
     prá
    -0.06
     Role
    -0.06
    　ノ
    -0.06
    POSITIVE LOGITS
     settlement
    0.07
     refreshing
    0.07
    대회
    0.06
     watching
    0.06
     requests
    0.06
     casually
    0.06
     settlements
    0.06
     squeezed
    0.06
     όμως
    0.06
    친
    0.06
    Act Density 0.005%

    No Known Activations