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

    Neuronpedia

    INDEX
    Explanations

    password change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Believe
    -0.07
    “When
    -0.06
     predatory
    -0.06
    كرة
    -0.06
    feit
    -0.06
     taxis
    -0.06
    -run
    -0.06
    Evaluate
    -0.06
     These
    -0.06
    method
    -0.06
    POSITIVE LOGITS
     upkeep
    0.07
    quad
    0.06
     renov
    0.06
     agreeing
    0.06
     regional
    0.06
     nhật
    0.06
     squads
    0.06
    oplevel
    0.06
     thuê
    0.06
    =NULL
    0.06
    Act Density 0.008%

    No Known Activations