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

    Neuronpedia

    INDEX
    Explanations

    Numerical and symbol data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ev
    -0.06
    "}}>↵
    -0.06
    Kick
    -0.06
     sexist
    -0.06
     lập
    -0.06
     marked
    -0.06
     clad
    -0.06
     lawyer
    -0.06
    +l
    -0.06
     örgüt
    -0.06
    POSITIVE LOGITS
     instantiated
    0.07
    еи
    0.07
    τή
    0.07
     skyrocket
    0.06
     Jeh
    0.06
    κι
    0.06
    Empleado
    0.06
    iete
    0.06
     cường
    0.06
     readiness
    0.06
    Act Density 0.002%

    No Known Activations