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

    Neuronpedia

    INDEX
    Explanations

    ink

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UGIN
    -0.07
    KE
    -0.07
     hb
    -0.06
    чили
    -0.06
     بالم
    -0.06
     paren
    -0.06
     birik
    -0.06
     dre
    -0.06
     gemacht
    -0.06
    496
    -0.06
    POSITIVE LOGITS
     forcing
    0.07
     sacrificing
    0.07
     Modi
    0.07
    龍
    0.06
    黄
    0.06
     Kong
    0.06
     Interfaces
    0.06
     getPassword
    0.06
    /YYYY
    0.06
     Investing
    0.06
    Act Density 0.000%

    No Known Activations