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

    Neuronpedia

    INDEX
    Explanations

    say "or"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    できます
    -0.07
    	Iterator
    -0.06
     مسائل
    -0.06
    Csv
    -0.06
     checkboxes
    -0.06
     восп
    -0.06
    ?p
    -0.06
     ApiService
    -0.06
    .capacity
    -0.06
     lista
    -0.06
    POSITIVE LOGITS
    \Controllers
    0.07
     comedic
    0.07
    0.07
     Lenovo
    0.06
    iffs
    0.06
    akens
    0.06
     gentle
    0.06
    ctica
    0.06
    roj
    0.06
    _bonus
    0.06
    Act Density 0.242%

    No Known Activations