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

    Neuronpedia

    INDEX
    Explanations

    computing machines and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     charismatic
    0.94
     marginalized
    0.93
     militias
    0.87
     minimalist
    0.85
     reimag
    0.85
     millennia
    0.84
     potentially
    0.84
     academia
    0.83
     nuanced
    0.83
     transformative
    0.82
    POSITIVE LOGITS
     furnishes
    1.34
     inasmuch
    1.15
    <0x11>
    1.08
     negroes
    1.06
     heretofore
    1.05
     advices
    1.03
    <0x0E>
    1.02
    ruary
    1.02
     compds
    1.00
     satisfactory
    1.00
    Act Density 0.000%

    No Known Activations