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

    Neuronpedia

    INDEX
    Explanations

    explaining actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ganggu
    0.59
     പ്രദേശ
    0.50
    glass
    0.50
     terapeut
    0.48
    னால
    0.48
     হতেই
    0.47
     ઉત્પાદ
    0.47
     ಬದಲ
    0.47
    ektiv
    0.47
    yaw
    0.46
    POSITIVE LOGITS
    1
    0.41
     lion
    0.40
    First
    0.40
    CO
    0.38
    Lion
    0.38
     \
    0.38
     leer
    0.38
     Ally
    0.38
    0
    0.38
     Sec
    0.37
    Act Density 0.000%

    No Known Activations