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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Designer
    -0.06
     labor
    -0.06
     mango
    -0.06
    izontal
    -0.06
    матрива
    -0.06
    _adc
    -0.06
    �부
    -0.06
     prosperity
    -0.06
    検
    -0.06
     quot
    -0.06
    POSITIVE LOGITS
     Richie
    0.07
     Melbourne
    0.06
    ))*
    0.06
    -max
    0.06
     substituted
    0.06
     reminded
    0.06
     有
    0.06
    ictionaries
    0.06
    ถม
    0.06
     Close
    0.06
    Act Density 0.005%

    No Known Activations