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

    Neuronpedia

    INDEX
    Explanations

    finding modules and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ária
    0.48
     Universität
    0.47
     Socialista
    0.47
     Tari
    0.46
    રી
    0.45
    ديث
    0.43
     Rheumat
    0.43
     Universities
    0.43
    époque
    0.43
     अपघात
    0.43
    POSITIVE LOGITS
     mobilize
    0.51
     bring
    0.49
     appease
    0.47
     जैसी
    0.47
     secures
    0.46
     brings
    0.45
     transmit
    0.45
     stabilize
    0.45
     negotiate
    0.45
     stays
    0.44
    Act Density 0.000%

    No Known Activations