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

    Neuronpedia

    INDEX
    Explanations

    closing brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шибка
    -0.06
     �
    -0.06
     एड
    -0.06
     fastest
    -0.06
     Het
    -0.06
     eat
    -0.06
     chiff
    -0.06
     Americ
    -0.06
     Зем
    -0.06
     社
    -0.06
    POSITIVE LOGITS
    ILITIES
    0.07
    prep
    0.06
     lô
    0.06
     Bomb
    0.06
    ++++++++++++++++
    0.06
     anthrop
    0.06
    @click
    0.06
    다가
    0.06
    hythm
    0.06
    AttributedString
    0.06
    Act Density 0.026%

    No Known Activations