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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tours
    -0.07
    .",↵
    -0.07
     moves
    -0.06
    set
    -0.06
     washed
    -0.06
    \Tests
    -0.06
     critic
    -0.06
    idae
    -0.06
     hoặc
    -0.06
     furniture
    -0.06
    POSITIVE LOGITS
     Physical
    0.07
    iband
    0.06
     Collaboration
    0.06
    ิงหาคม
    0.06
    trys
    0.06
     Consent
    0.06
    :NS
    0.06
    _stub
    0.06
    lessly
    0.06
    ард
    0.06
    Act Density 0.009%

    No Known Activations