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

    Neuronpedia

    INDEX
    Explanations

    project scope and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acide
    0.44
     KNO
    0.42
     acidification
    0.42
     reflecting
    0.41
     উ
    0.41
     according
    0.41
     November
    0.40
     Sein
    0.40
     Yuan
    0.40
    িসি
    0.40
    POSITIVE LOGITS
    ِّف
    0.43
     jeopardize
    0.42
     času
    0.40
     मैचों
    0.39
    อบคุณ
    0.39
     mischiev
    0.39
    JUnit
    0.38
     overlooked
    0.38
     ponú
    0.38
     mischievous
    0.37
    Act Density 0.011%

    No Known Activations