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

    Neuronpedia

    INDEX
    Explanations

    Scientific publication identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    01
    -0.07
    čná
    -0.07
    08
    -0.06
    o
    -0.06
    04
    -0.06
     explo
    -0.06
     obt
    -0.06
     funkce
    -0.06
    -No
    -0.06
     served
    -0.06
    POSITIVE LOGITS
     Tumblr
    0.07
     indispensable
    0.07
    Authentication
    0.06
     mistress
    0.06
     hak
    0.06
    Tar
    0.06
     Forgotten
    0.06
    padding
    0.06
     Thickness
    0.06
    　ﾊ
    0.06
    Act Density 0.016%

    No Known Activations