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

    Neuronpedia

    INDEX
    Explanations

    introductions and welcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assistant
    -0.07
     Imm
    -0.06
     electronically
    -0.06
     přib
    -0.06
    description
    -0.06
    imen
    -0.06
     attracting
    -0.06
    둥
    -0.06
    ediği
    -0.06
     bakım
    -0.06
    POSITIVE LOGITS
    ="<<
    0.07
     解
    0.06
    erve
    0.06
     "==
    0.06
    :"#
    0.06
     '#
    0.06
     pró
    0.06
    ERVED
    0.06
    .!
    0.06
     متف
    0.06
    Act Density 0.023%

    No Known Activations