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

    Neuronpedia

    INDEX
    Explanations

    code questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reusable
    -0.07
    heimer
    -0.07
    amoto
    -0.06
     нег
    -0.06
     halde
    -0.06
    hipster
    -0.06
     δεν
    -0.06
    Royal
    -0.06
    (/^\
    -0.06
    $\
    -0.05
    POSITIVE LOGITS
    alesce
    0.07
     gardening
    0.07
     Kind
    0.07
     Flash
    0.06
    UGH
    0.06
     REC
    0.06
    ーター
    0.06
     godt
    0.06
    .Startup
    0.06
     appreciate
    0.06
    Act Density 0.026%

    No Known Activations