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

    Neuronpedia

    INDEX
    Explanations

    Tell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mak
    -0.07
    .val
    -0.07
    banks
    -0.07
     cholesterol
    -0.07
     Harbour
    -0.07
    ılıp
    -0.06
     republika
    -0.06
    [::-
    -0.06
    cosity
    -0.06
    vae
    -0.06
    POSITIVE LOGITS
     contracted
    0.07
    यह
    0.06
     요구
    0.06
    ье
    0.06
     FUNC
    0.06
    ез
    0.06
     �
    0.06
     URLs
    0.06
    이었
    0.06
     perg
    0.06
    Act Density 0.031%

    No Known Activations