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

    Neuronpedia

    INDEX
    Explanations

    Permissions and requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bahamas
    -0.07
     exhibitions
    -0.06
     TYPE
    -0.06
     shrink
    -0.06
    .write
    -0.06
     accuracy
    -0.06
    _matrices
    -0.06
     embody
    -0.06
     PARTIC
    -0.06
     grid
    -0.06
    POSITIVE LOGITS
     проф
    0.07
    Chicken
    0.07
    Ơ
    0.06
    Cu
    0.06
    銀
    0.06
    Hands
    0.06
     occured
    0.06
    (nt
    0.06
    (Parse
    0.06
     způsob
    0.06
    Act Density 0.019%

    No Known Activations