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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manages
    -0.07
    .Write
    -0.06
     řekl
    -0.06
     currentPage
    -0.06
     admitting
    -0.06
     ulcer
    -0.06
     chew
    -0.06
     speak
    -0.06
    @Inject
    -0.06
    ंश
    -0.06
    POSITIVE LOGITS
     doom
    0.07
     getpid
    0.06
     proofs
    0.06
     분
    0.06
     fld
    0.06
     상태
    0.06
    ################################
    0.06
    공지
    0.06
     stripped
    0.06
     vas
    0.06
    Act Density 0.015%

    No Known Activations