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

    Neuronpedia

    INDEX
    Explanations

    communication verbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terdapat
    0.61
     zunehm
    0.57
     "%
    0.53
    Discuss
    0.52
     increasingly
    0.52
     Discuss
    0.51
     চতু
    0.51
     interacting
    0.50
     Relatively
    0.50
     অংশগ্রহণ
    0.49
    POSITIVE LOGITS
     warned
    1.44
     gave
    1.34
     insisted
    1.33
     told
    1.31
     asked
    1.22
     promised
    1.22
     taught
    1.16
     said
    1.11
     suggested
    1.11
     swore
    1.07
    Act Density 0.115%

    No Known Activations