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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bp
    -0.07
    cer
    -0.07
     catalyst
    -0.07
     bombs
    -0.07
    _Al
    -0.07
     vinc
    -0.07
     barring
    -0.07
     stems
    -0.07
     paints
    -0.07
    申
    -0.07
    POSITIVE LOGITS
    _MED
    0.07
    gne
    0.07
    🗿
    0.07
    ᴉ
    0.07
     Espresso
    0.07
     erreur
    0.07
    骜
    0.06
    自此
    0.06
    ☫
    0.06
     segundos
    0.06
    Act Density 0.024%

    No Known Activations