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

    Neuronpedia

    INDEX
    Explanations

    don

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    losing
    -0.07
     sembl
    -0.06
     CONTROL
    -0.06
    illard
    -0.06
    -running
    -0.06
    ilon
    -0.06
     Mev
    -0.06
     Classified
    -0.06
     Registro
    -0.06
     Control
    -0.06
    POSITIVE LOGITS
    -dir
    0.06
    LayoutParams
    0.06
     payroll
    0.06
    にと
    0.06
     жінок
    0.06
    不到
    0.06
     $.
    0.06
    },
    0.06
    skins
    0.06
    @param
    0.06
    Act Density 0.000%

    No Known Activations