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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hier
    -0.07
     charitable
    -0.06
     svých
    -0.06
     INTO
    -0.06
     />↵↵
    -0.06
    loading
    -0.06
     inward
    -0.06
    rema
    -0.06
    otron
    -0.06
     внес
    -0.06
    POSITIVE LOGITS
     Computers
    0.07
     Collaboration
    0.07
     protested
    0.07
     Claw
    0.07
    languages
    0.07
     protester
    0.07
     correcting
    0.07
     partnership
    0.06
     photo
    0.06
     Creates
    0.06
    Act Density 0.006%

    No Known Activations