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

    Neuronpedia

    INDEX
    Explanations

    ina

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /umd
    -0.07
     Yup
    -0.07
     засід
    -0.07
     ویرایش
    -0.06
    Trip
    -0.06
    –↵↵
    -0.06
     Арх
    -0.06
     Пра
    -0.06
     gül
    -0.06
    	dis
    -0.06
    POSITIVE LOGITS
    taking
    0.07
    �
    0.06
    ัส
    0.06
    acam
    0.06
    ains
    0.06
    opaque
    0.06
    ién
    0.06
    odos
    0.06
    ze
    0.06
    ũ
    0.06
    Act Density 0.001%

    No Known Activations