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

    Neuronpedia

    INDEX
    Explanations

    Code/Strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ISS
    -0.07
    Cho
    -0.07
     ztr
    -0.06
    _format
    -0.06
    .PL
    -0.06
    け
    -0.06
     ث
    -0.06
     aff
    -0.06
     »↵↵
    -0.06
    FromClass
    -0.06
    POSITIVE LOGITS
     setValue
    0.07
     Cafe
    0.07
    yyval
    0.07
     toto
    0.07
    SEARCH
    0.06
    oucher
    0.06
     entrepreneur
    0.06
    :checked
    0.06
     ohio
    0.06
     fooled
    0.06
    Act Density 0.032%

    No Known Activations