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

    Neuronpedia

    INDEX
    Explanations

    JavaScript element creation and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നിന്ന്
    0.63
     atento
    0.58
     construye
    0.57
     वाणी
    0.51
     반려
    0.50
    लीकरण
    0.50
     Oost
    0.48
     atentos
    0.48
    بینی
    0.48
    ometraje
    0.48
    POSITIVE LOGITS
     );
    0.61
    which
    0.57
     )
    0.50
     WHICH
    0.50
     ).
    0.50
    God
    0.48
    为其
    0.47
                 
    0.46
     premises
    0.46
    ok
    0.45
    Act Density 0.001%

    No Known Activations