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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mats
    -0.07
    “One
    -0.07
     camino
    -0.07
    drive
    -0.07
    _ai
    -0.06
     Springfield
    -0.06
     shoot
    -0.06
    -share
    -0.06
     slippery
    -0.06
     había
    -0.06
    POSITIVE LOGITS
    NS
    0.07
     expenditures
    0.06
    .loader
    0.06
    แห
    0.06
    ;]/
    0.06
    idenav
    0.06
    แข
    0.06
    Below
    0.06
     coin
    0.06
    opyright
    0.06
    Act Density 0.062%

    No Known Activations