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

    Neuronpedia

    INDEX
    Explanations

    predict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /oct
    -0.07
    Credentials
    -0.07
     Inner
    -0.07
    Road
    -0.07
     fonts
    -0.06
     Frontier
    -0.06
    _root
    -0.06
    AWN
    -0.06
    buyer
    -0.06
    Chem
    -0.06
    POSITIVE LOGITS
     зрения
    0.09
    �
    0.07
    .fetchone
    0.07
     asserted
    0.06
     distinctly
    0.06
    )$_
    0.06
     이러
    0.06
    .В
    0.06
     entender
    0.06
     hare
    0.06
    Act Density 0.241%

    No Known Activations