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

    Neuronpedia

    INDEX
    Explanations

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Similarly
    0.51
     similarly
    0.51
     zuerst
    0.50
    したり
    0.49
    ளிலும்
    0.47
     Gruppe
    0.47
     दूसरा
    0.46
     것도
    0.45
     or
    0.44
     osim
    0.44
    POSITIVE LOGITS
     downright
    0.60
     infine
    0.59
     importantly
    0.58
     अगदी
    0.56
     przede
    0.52
    最後に
    0.51
    Finally
    0.50
     любви
    0.49
     crucially
    0.48
     lastly
    0.48
    Act Density 0.146%

    No Known Activations