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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .qu
    -0.07
    +'"
    -0.06
    setProperty
    -0.06
     requ
    -0.06
     Korean
    -0.06
     juego
    -0.06
     milk
    -0.06
    ládá
    -0.06
     coop
    -0.06
     Creature
    -0.06
    POSITIVE LOGITS
     assorted
    0.07
     طبقه
    0.07
     albeit
    0.07
    овід
    0.07
     dolor
    0.06
    生命
    0.06
    _gchandle
    0.06
    �
    0.06
    さ
    0.06
     contrat
    0.06
    Act Density 0.016%

    No Known Activations