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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extensive
    -0.07
     enable
    -0.07
    customer
    -0.07
     damning
    -0.06
     Fay
    -0.06
    privileged
    -0.06
     usual
    -0.06
     Spider
    -0.06
     getStatus
    -0.06
     consisting
    -0.06
    POSITIVE LOGITS
    etooth
    0.07
     clas
    0.07
    الا
    0.07
     Drake
    0.06
    �
    0.06
    巴
    0.06
    ↓
    0.06
    (withId
    0.06
    �
    0.06
     stř
    0.06
    Act Density 0.005%

    No Known Activations