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

    Neuronpedia

    INDEX
    Explanations

    but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    therefore
    0.67
     therefore
    0.61
     zwar
    0.61
     λοι
    0.57
    Therefore
    0.56
    雖然
    0.55
     dunque
    0.55
     tehát
    0.55
     infatti
    0.54
     quindi
    0.53
    POSITIVE LOGITS
     also
    0.84
     మాత్రం
    0.80
     också
    0.78
     nonetheless
    0.77
     myös
    0.76
     también
    0.75
     também
    0.74
     nevertheless
    0.73
     juga
    0.72
     też
    0.72
    Act Density 0.023%

    No Known Activations