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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -License
    -0.07
     Wheeler
    -0.07
    uales
    -0.07
     Riders
    -0.07
    itsu
    -0.07
     sovereignty
    -0.07
    ुए
    -0.07
     naopak
    -0.06
     understanding
    -0.06
     Dickinson
    -0.06
    POSITIVE LOGITS
     saldo
    0.06
     في
    0.06
    �
    0.06
    -inner
    0.06
    croll
    0.06
     matlab
    0.06
    /c
    0.06
    _EMP
    0.06
     sincerely
    0.05
     elder
    0.05
    Act Density 0.005%

    No Known Activations