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

    Neuronpedia

    INDEX
    Explanations

    truly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आस
    -0.07
    orrent
    -0.07
     NotificationCenter
    -0.07
    interopRequire
    -0.07
    iqueta
    -0.06
    _rand
    -0.06
    _checkbox
    -0.06
     apare
    -0.06
     isEmpty
    -0.06
     zaw
    -0.06
    POSITIVE LOGITS
     truly
    0.13
     Truly
    0.09
    _TUN
    0.07
     OF
    0.06
     ку
    0.06
    (predictions
    0.06
     enlist
    0.06
     ultimately
    0.06
     demographics
    0.06
     traged
    0.06
    Act Density 0.005%

    No Known Activations