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

    Neuronpedia

    INDEX
    Explanations

    recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     is
    -0.07
    (filtered
    -0.07
     are
    -0.07
     前
    -0.06
     addTo
    -0.06
     has
    -0.06
     spite
    -0.06
     isn
    -0.06
    前
    -0.06
     HF
    -0.06
    POSITIVE LOGITS
     DAM
    0.07
     [/
    0.07
    -tip
    0.06
     Tomato
    0.06
     revolves
    0.06
    %'
    0.06
    Station
    0.06
    thew
    0.06
    936
    0.06
    ISMATCH
    0.06
    Act Density 0.469%

    No Known Activations