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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voice
    -0.07
    อย
    -0.07
     Proto
    -0.06
     squad
    -0.06
    Guy
    -0.06
    	Value
    -0.06
    elope
    -0.06
     Bear
    -0.06
     Orient
    -0.06
     voiced
    -0.06
    POSITIVE LOGITS
    _PP
    0.07
    يير
    0.07
    فات
    0.07
    孔
    0.07
    ystate
    0.06
    izoph
    0.06
    bach
    0.06
    _svc
    0.06
    .so
    0.06
    า�
    0.06
    Act Density 0.025%

    No Known Activations