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

    Neuronpedia

    INDEX
    Explanations

    ==

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revenge
    -0.07
     striped
    -0.07
     sings
    -0.07
     FAT
    -0.07
     karma
    -0.07
    ');
↵
↵
    -0.07
    ερμαν
    -0.06
     Activities
    -0.06
    <td
    -0.06
     их
    -0.06
    POSITIVE LOGITS
     Maher
    0.06
    /jpeg
    0.06
    атель
    0.06
    GRADE
    0.06
    ESTAMP
    0.06
     Mov
    0.06
     Certified
    0.06
    .isNull
    0.06
    <::
    0.06
     Intelli
    0.06
    Act Density 0.025%

    No Known Activations