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

    Neuronpedia

    INDEX
    Explanations

    historical events, places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temptation
    -0.08
     Twelve
    -0.07
    車
    -0.07
     Truth
    -0.06
    미
    -0.06
    фф
    -0.06
     Dez
    -0.06
    Com
    -0.06
     사람
    -0.06
     Lord
    -0.06
    POSITIVE LOGITS
     Hãy
    0.07
     Δια
    0.06
    program
    0.06
     Interviews
    0.06
     EINVAL
    0.06
    „J
    0.06
     отдель
    0.06
     percept
    0.06
    hua
    0.06
    opause
    0.06
    Act Density 0.094%

    No Known Activations