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

    Neuronpedia

    INDEX
    Explanations

    code input/output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'яз
    -0.07
     Encore
    -0.07
     Advisory
    -0.06
    tones
    -0.06
    .lbl
    -0.06
    Wis
    -0.06
    िद
    -0.06
    во
    -0.06
    SUPER
    -0.06
    γον
    -0.06
    POSITIVE LOGITS
     širo
    0.07
     Gson
    0.06
     darf
    0.06
    ☴
    0.06
     classe
    0.06
    ~-~-~-~-
    0.06
     instantly
    0.06
     hairs
    0.06
     drummer
    0.06
     Malay
    0.06
    Act Density 0.074%

    No Known Activations