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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Typed
    -0.07
    stalk
    -0.07
     AAC
    -0.06
     Сред
    -0.06
    ozilla
    -0.06
     distinct
    -0.06
     Scri
    -0.06
    DAQ
    -0.06
     فارس
    -0.06
    /rfc
    -0.06
    POSITIVE LOGITS
    년에
    0.08
     music
    0.07
    WithEmailAndPassword
    0.07
    684
    0.06
     screw
    0.06
     الکتر
    0.06
     bö
    0.06
     بل
    0.06
    controllers
    0.06
     Поль
    0.06
    Act Density 0.014%

    No Known Activations