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

    Neuronpedia

    INDEX
    Explanations

    Blog excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arsenal
    -0.07
     <>↵
    -0.07
    myModalLabel
    -0.07
    .respond
    -0.06
    	con
    -0.06
     SINGLE
    -0.06
    -Bar
    -0.06
     cần
    -0.06
    ======
    -0.06
     Taking
    -0.06
    POSITIVE LOGITS
    clipse
    0.07
     discret
    0.07
    utz
    0.06
     interrog
    0.06
     meters
    0.06
     aur
    0.06
     tecr
    0.06
    wor
    0.06
     Sue
    0.06
     FINSEQ
    0.06
    Act Density 0.038%

    No Known Activations