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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Command
    -0.07
    skills
    -0.07
    Anime
    -0.06
     pistols
    -0.06
    Drag
    -0.06
     nu
    -0.06
    ين
    -0.06
    aption
    -0.06
    шел
    -0.06
     win
    -0.06
    POSITIVE LOGITS
     Democr
    0.06
    _fact
    0.06
     موارد
    0.06
     nominated
    0.06
    つぶ
    0.06
    -unstyled
    0.06
     Beng
    0.06
    adora
    0.06
     und
    0.06
     alimentos
    0.06
    Act Density 0.035%

    No Known Activations