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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remaining
    -0.08
     inward
    -0.08
     previsto
    -0.07
     �
    -0.07
     steep
    -0.07
    ATOM
    -0.07
     fom
    -0.07
     forman
    -0.07
     tụ
    -0.07
     agentes
    -0.07
    POSITIVE LOGITS
     Benedict
    0.08
     Bible
    0.08
    geving
    0.08
     Monde
    0.08
     Genesis
    0.08
     Galaxy
    0.07
     Shadow
    0.07
     Testimonials
    0.07
     Zusatz
    0.07
     Augsburg
    0.07
    Act Density 0.005%

    No Known Activations