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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =S
    -0.06
     안
    -0.06
     fried
    -0.06
    %S
    -0.06
     exile
    -0.06
    .opengl
    -0.06
     inadvertently
    -0.06
    意味
    -0.06
    怕
    -0.06
     bland
    -0.06
    POSITIVE LOGITS
     password
    0.07
     Valid
    0.07
     supposed
    0.06
     Absolutely
    0.06
    .');↵
    0.06
    _host
    0.06
    .TEXTURE
    0.06
    .overflow
    0.06
    actors
    0.06
     Veter
    0.06
    Act Density 0.028%

    No Known Activations