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

    Neuronpedia

    INDEX
    Explanations

    waiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	items
    -0.07
     полот
    -0.06
    hong
    -0.06
    _out
    -0.06
    (bl
    -0.06
     Nir
    -0.06
     Invalidate
    -0.06
    hra
    -0.06
     Bạn
    -0.06
     Sacr
    -0.06
    POSITIVE LOGITS
     دف
    0.08
    recision
    0.07
     Vocal
    0.07
    .Forms
    0.06
     뉴
    0.06
    .todo
    0.06
    iasm
    0.06
     bearings
    0.06
     Islanders
    0.06
     lett
    0.06
    Act Density 0.007%

    No Known Activations