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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salle
    -0.07
     intellig
    -0.07
    覚
    -0.07
    -money
    -0.07
     anale
    -0.07
    Italic
    -0.06
     uzak
    -0.06
    ektedir
    -0.06
    another
    -0.06
    分
    -0.06
    POSITIVE LOGITS
     sab
    0.07
    _bar
    0.06
     Hor
    0.06
     mash
    0.06
    uo
    0.06
     smashing
    0.06
    иф
    0.06
    ]|[
    0.06
     Mash
    0.06
    _callback
    0.06
    Act Density 0.000%

    No Known Activations