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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -IN
    -0.07
     decline
    -0.07
     emergence
    -0.07
     acquisition
    -0.07
    �
    -0.07
    434
    -0.07
     declined
    -0.07
     catapult
    -0.06
     Manus
    -0.06
     ruined
    -0.06
    POSITIVE LOGITS
    _BOTTOM
    0.07
    passport
    0.07
    stantial
    0.07
    .wallet
    0.06
    ROL
    0.06
    islation
    0.06
     brawl
    0.06
     인터넷
    0.06
     ticaret
    0.06
    .getColor
    0.06
    Act Density 0.062%

    No Known Activations