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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     בחדר
    -0.08
     vrij
    -0.08
    רוס
    -0.07
    Pear
    -0.07
    Slug
    -0.07
     hosp
    -0.07
    _Version
    -0.07
     glazed
    -0.07
     Swal
    -0.07
    swagger
    -0.07
    POSITIVE LOGITS
     regulatory
    0.07
     tuning
    0.07
    핟
    0.07
    𝓃
    0.07
    ﳜ
    0.07
    𝓭
    0.07
     uni
    0.07
     Lingu
    0.07
     athe
    0.06
     jmp
    0.06
    Act Density 0.006%

    No Known Activations