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

    Neuronpedia

    INDEX
    Explanations

    cro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buzz
    -0.07
     condoms
    -0.07
     DD
    -0.07
    	damage
    -0.07
     SwiftUI
    -0.06
    lilik
    -0.06
     zpráva
    -0.06
    berg
    -0.06
    지만
    -0.06
     zv
    -0.06
    POSITIVE LOGITS
    ilet
    0.07
     αξ
    0.07
     маг
    0.07
    えた
    0.06
     Competitive
    0.06
    Fourth
    0.06
    Pago
    0.06
    ellidos
    0.06
     αγ
    0.06
    checked
    0.06
    Act Density 0.002%

    No Known Activations