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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiplayer
    -0.07
    Encrypt
    -0.07
     emotionally
    -0.06
    jít
    -0.06
    romosome
    -0.06
     fileprivate
    -0.06
    expect
    -0.06
     바람
    -0.06
    tam
    -0.05
    .”
    -0.05
    POSITIVE LOGITS
     uninsured
    0.08
    iting
    0.07
    default
    0.07
    -Ray
    0.07
       
    0.07
     purge
    0.07
     Jeff
    0.07
     scoop
    0.07
    undler
    0.07
     teplot
    0.07
    Act Density 0.001%

    No Known Activations