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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    首领
    -0.07
    留守
    -0.07
     judged
    -0.07
     nutrit
    -0.07
     тебя
    -0.07
    OLOR
    -0.07
    冲刺
    -0.07
    [input
    -0.07
     spawns
    -0.06
     suma
    -0.06
    POSITIVE LOGITS
    phon
    0.08
    �
    0.08
     GHC
    0.07
    -client
    0.07
     ธ
    0.07
    世
    0.07
    .Cloud
    0.07
     Hibernate
    0.07
     CZ
    0.07
    .pitch
    0.07
    Act Density 0.077%

    No Known Activations