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

    Neuronpedia

    INDEX
    Explanations

    political consequences, feeling range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    por
    0.44
    ica
    0.39
    velopment
    0.39
    NOTES
    0.37
    AT
    0.37
    notes
    0.36
    ori
    0.36
    aste
    0.35
    mano
    0.35
    IT
    0.35
    POSITIVE LOGITS
    शिंगटन
    0.45
    !`
    0.44
     başar
    0.44
     फिगर
    0.43
    㗆
    0.40
     በኋላ
    0.39
     benefitting
    0.39
    Exponent
    0.39
     beneficia
    0.39
     Criticism
    0.38
    Act Density 0.000%

    No Known Activations