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

    Neuronpedia

    INDEX
    Explanations

    message or tagline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inhomogeneous
    0.80
    かれる
    0.73
    かれた
    0.69
    infested
    0.68
    наў
    0.67
     பிரதேச
    0.65
     blom
    0.65
    uslar
    0.64
    AcOH
    0.63
    larghezza
    0.63
    POSITIVE LOGITS
     message
    1.68
     messaging
    1.60
     Message
    1.45
    message
    1.44
     tagline
    1.43
     messages
    1.43
     promises
    1.43
     promise
    1.37
     Messaging
    1.36
    Message
    1.35
    Act Density 1.069%

    No Known Activations