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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     departure
    -0.07
    BOSE
    -0.06
     Lean
    -0.06
     FTP
    -0.06
    빌
    -0.06
     rulings
    -0.06
    죄
    -0.06
    VERIFY
    -0.06
     leather
    -0.06
    trans
    -0.06
    POSITIVE LOGITS
    _TURN
    0.07
    	emit
    0.06
    _stop
    0.06
     overturn
    0.06
    _ray
    0.06
    CTION
    0.06
     podcasts
    0.06
     projectile
    0.06
    _op
    0.06
     Před
    0.06
    Act Density 0.001%

    No Known Activations