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

    Neuronpedia

    INDEX
    Explanations

    tabular data separated by pipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saison
    0.36
     euph
    0.35
     }=\
    0.35
     doxycycline
    0.35
     cins
    0.35
    }=\
    0.34
     cheesecake
    0.34
     fazem
    0.34
     resusc
    0.34
     oneness
    0.34
    POSITIVE LOGITS
    <tr>
    0.36
    <0x0D>
    0.36
    ;
    0.34
    ↵
    0.33
     Elast
    0.33
     Even
    0.33
    o
    0.33
    .`
    0.33
    .$
    0.32
    code
    0.31
    Act Density 0.000%

    No Known Activations