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

    Neuronpedia

    INDEX
    Explanations

    hardware

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     cleansing
    -0.07
     Locator
    -0.07
    oppable
    -0.06
     detox
    -0.06
     Kids
    -0.06
    finish
    -0.06
     Official
    -0.06
    institution
    -0.06
     повинні
    -0.06
    POSITIVE LOGITS
    hardware
    0.08
     hardware
    0.07
    慧
    0.07
     Harry
    0.07
    毕业
    0.07
    �
    0.07
    женер
    0.07
     HACK
    0.07
     schvál
    0.07
     trí
    0.07
    Act Density 0.007%

    No Known Activations