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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commodo
    -0.07
     politic
    -0.06
     dispro
    -0.06
    обрет
    -0.06
    -spot
    -0.06
    dims
    -0.06
     embod
    -0.06
     slideshow
    -0.06
    NavBar
    -0.06
     heroin
    -0.06
    POSITIVE LOGITS
     educated
    0.07
    atars
    0.07
     endings
    0.07
     mh
    0.06
     pev
    0.06
    assy
    0.06
     cuer
    0.06
    persons
    0.06
    (DB
    0.06
    .Mon
    0.06
    Act Density 0.000%

    No Known Activations