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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ye
    -0.07
    �
    -0.06
    ']:
    -0.06
     efficiencies
    -0.06
     nombres
    -0.06
    /"+
    -0.06
    ensation
    -0.06
    <D
    -0.06
     bip
    -0.06
     saber
    -0.06
    POSITIVE LOGITS
    مو
    0.08
    etime
    0.07
    ρει
    0.07
     herein
    0.06
    classpath
    0.06
     Кра
    0.06
    roman
    0.06
     defamation
    0.06
     clazz
    0.06
     پشت
    0.06
    Act Density 0.009%

    No Known Activations