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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     problemas
    -0.07
    Psi
    -0.06
    /swagger
    -0.06
     Entre
    -0.06
     Que
    -0.06
     deform
    -0.06
     Parr
    -0.06
     presente
    -0.06
    烟
    -0.06
     destac
    -0.06
    POSITIVE LOGITS
     Grinding
    0.07
     Licensing
    0.07
    "fmt
    0.06
     worthwhile
    0.06
    stdcall
    0.06
    ?><?
    0.06
    ****************************************************************************
    0.06
    PCR
    0.06
    �
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations