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

    Neuronpedia

    INDEX
    Explanations

    until

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REATED
    -0.07
    aname
    -0.07
     mắt
    -0.07
    พยาบาล
    -0.07
    ,array
    -0.07
    ponce
    -0.07
     laut
    -0.06
     garbage
    -0.06
     heartfelt
    -0.06
    agic
    -0.06
    POSITIVE LOGITS
     demolished
    0.07
    GR
    0.06
    		  ↵
    0.06
     Joshua
    0.06
     Regulations
    0.06
    707
    0.06
     Mig
    0.06
     ProductService
    0.06
    .WaitFor
    0.06
     XIV
    0.06
    Act Density 0.015%

    No Known Activations