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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roles
    -0.08
     Killed
    -0.07
     Ethics
    -0.07
    Desktop
    -0.07
    director
    -0.06
     Roles
    -0.06
    ="<?
    -0.06
     dostup
    -0.06
    ским
    -0.06
     Accounting
    -0.06
    POSITIVE LOGITS
     تلك
    0.07
     signage
    0.06
    emotion
    0.06
     hormonal
    0.06
    210
    0.06
    erialization
    0.06
    wanted
    0.06
    ForObject
    0.06
     microwave
    0.06
     Irr
    0.06
    Act Density 0.021%

    No Known Activations