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

    Neuronpedia

    INDEX
    Explanations

    #define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hiç
    -0.07
    「你
    -0.07
    緒
    -0.07
     Colonial
    -0.06
    �行
    -0.06
    =color
    -0.06
    „ط
    -0.06
     Rubber
    -0.06
     housed
    -0.06
    _ticket
    -0.06
    POSITIVE LOGITS
     unlucky
    0.06
    _can
    0.06
    EMU
    0.06
     Austral
    0.06
    ATT
    0.06
    Dave
    0.06
    -start
    0.06
    ddie
    0.06
    emu
    0.06
    Jon
    0.06
    Act Density 0.005%

    No Known Activations