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

    Neuronpedia

    INDEX
    Explanations

    call to action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     полиции
    0.42
    িনি
    0.39
    铒
    0.38
    SLOW
    0.38
     పోలీసులు
    0.37
    FBSDKError
    0.37
    贄
    0.37
    RNB
    0.36
    Salmon
    0.36
    ន្ល
    0.36
    POSITIVE LOGITS
     Learn
    0.86
     LEARN
    0.82
     learn
    0.79
     Download
    0.77
    Learn
    0.76
    learn
    0.73
    Download
    0.70
     download
    0.68
     sign
    0.68
     Enroll
    0.67
    Act Density 0.004%

    No Known Activations