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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shakspeare
    -1.26
     Efq
    -1.22
     uſed
    -1.17
     Monfieur
    -1.16
     myſelf
    -1.11
     متعلقه
    -1.08
     doubtnut
    -1.07
     designed
    -1.05
     Houſe
    -1.05
     Shaksp
    -1.04
    POSITIVE LOGITS
     final
    0.69
     
    0.68
     I
    0.64
     N
    0.63
     Ch
    0.61
     tr
    0.61
     Go
    0.61
     R
    0.59
     sub
    0.59
     $\
    0.59
    Act Density 0.166%

    No Known Activations