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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zt
    -0.07
     stripping
    -0.06
     Plenty
    -0.06
    (cx
    -0.06
     crashing
    -0.06
     insecurity
    -0.06
     Vys
    -0.06
     них
    -0.06
     getTitle
    -0.06
     cores
    -0.06
    POSITIVE LOGITS
    …↵↵↵↵
    0.07
     Leave
    0.07
    ()},↵
    0.07
    은
    0.06
    ifikace
    0.06
    apollo
    0.06
    ...)↵↵
    0.06
     Lara
    0.06
     quelques
    0.06
     Hebrew
    0.06
    Act Density 0.000%

    No Known Activations