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

    Neuronpedia

    INDEX
    Explanations

    Boilers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ridge
    -0.06
    Cert
    -0.06
    Rest
    -0.06
    Snow
    -0.06
     TRAN
    -0.06
    -ms
    -0.06
    併
    -0.06
    ===↵
    -0.06
     according
    -0.06
    持
    -0.06
    POSITIVE LOGITS
     отдель
    0.07
     člov
    0.07
     página
    0.07
     vás
    0.07
     impart
    0.06
    .entries
    0.06
     şöyle
    0.06
    _ASYNC
    0.06
    .assert
    0.06
    	ctrl
    0.06
    Act Density 0.121%

    No Known Activations