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

    Neuronpedia

    INDEX
    Explanations

    representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ETH
    -0.07
     blonde
    -0.07
     six
    -0.07
     doors
    -0.07
     Hud
    -0.06
     winter
    -0.06
     aisle
    -0.06
     deals
    -0.06
    654
    -0.06
     summer
    -0.06
    POSITIVE LOGITS
    repr
    0.08
     devoid
    0.07
     uniquely
    0.07
     기반
    0.07
    render
    0.07
    dration
    0.06
    forma
    0.06
    417
    0.06
     padr
    0.06
     fortress
    0.06
    Act Density 0.009%

    No Known Activations