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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.82
     
    -0.77
    ,
    -0.68
     in
    -0.56
     I
    -0.54
     M
    -0.52
     and
    -0.52
     a
    -0.52
     -
    -0.51
     насељу
    -0.49
    POSITIVE LOGITS
     itſelf
    1.19
     Jefus
    1.03
     houſe
    1.02
     Houſe
    1.00
     Efq
    0.99
     ſtate
    0.96
     photolibrary
    0.95
     myſelf
    0.95
    ſelf
    0.94
     themſelves
    0.94
    Act Density 0.192%

    No Known Activations