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
     print
    -0.06
     FRIEND
    -0.06
    Free
    -0.06
     intern
    -0.06
     Guns
    -0.06
    !»
    -0.06
     eskorte
    -0.06
    hare
    -0.06
    ัณฑ
    -0.06
    -post
    -0.06
    POSITIVE LOGITS
     SDS
    0.07
     bios
    0.07
     Bios
    0.07
     Brewers
    0.07
     ışık
    0.07
     elic
    0.07
     huis
    0.07
    iqueta
    0.06
    YPD
    0.06
     restTemplate
    0.06
    Act Density 0.004%

    No Known Activations