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
     again
    -0.08
     bąd
    -0.07
     })
↵
    -0.07
    �
    -0.07
     recap
    -0.07
     heel
    -0.07
     redistribute
    -0.07
     incapable
    -0.07
     funnel
    -0.07
     across
    -0.07
    POSITIVE LOGITS
    (equalTo
    0.08
    essional
    0.07
     Comics
    0.07
    改革
    0.07
    תן
    0.07
    学会
    0.07
    wahl
    0.07
     являются
    0.07
    -care
    0.07
    elfast
    0.07
    Act Density 0.020%

    No Known Activations